abink/Tumor_Classification

1{"cells":[{"cell_type":"markdown","source":["# **Brain MRI Tumor Classification Using DenseNet121 Transfer Learning**"],"metadata":{"id":"kFRakAU-uEOm"}},{"cell_type":"markdown","source":["DenseNet121 was investigated because dense feature reuse can be useful for medical image classification."],"metadata":{"id":"rs5cGtfcuYvj"}},{"cell_type":"markdown","source":["# **Architecture**\n","\n","DenseNet121 (ImageNet pretrained) → GlobalAveragePooling2D → Dense(256) + BatchNorm + Dropout(0.4) → Dense(128) + BatchNorm + Dropout(0.3) → Dense(4, Softmax)\n","\n","# **Fine-tuning investigation**\n","\n","The initial fine-tuning strategy reduced performance: **83% → 79%**\n","\n","A more conservative strategy was subsequently tested:\n","Later DenseNet layers unfrozen from conv5_block9, BatchNormalization layers kept frozen, AdamW optimizer, Learning rate: 3e-6, Weight decay: 1e-4, Early stopping, ReduceLROnPlateau\n","\n","\n","This recovered performance to **83%**, but did not produce a meaningful improvement over the frozen-backbone model."],"metadata":{"id":"BFzmHRHRwScS"}},{"cell_type":"code","source":[],"metadata":{"id":"QdopPT_YyWI4"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"qjQrXUwrIZdN"},"source":["**Libraries and datasets**"]},{"cell_type":"code","execution_count":1,"metadata":{"executionInfo":{"elapsed":4845,"status":"ok","timestamp":1787474391727,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"},"user_tz":-330},"id":"dVQpaeHGI1eK"},"outputs":[],"source":["import tensorflow as tf\n","from tensorflow.keras.models import Sequential\n","from tensorflow.keras.layers import Input, Flatten, Dropout, Dense, GlobalAveragePooling2D, BatchNormalization\n","from tensorflow.keras.optimizers import Adam\n","from tensorflow.keras.applications import DenseNet121"]},{"cell_type":"code","source":["import os\n","import random"],"metadata":{"id":"cRXa2A8v7Lmy","executionInfo":{"status":"ok","timestamp":1787474391732,"user_tz":-330,"elapsed":3,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":2,"outputs":[]},{"cell_type":"code","source":["from PIL import Image, ImageEnhance\n","from tensorflow.keras.preprocessing.image import load_img\n","from sklearn.utils import shuffle"],"metadata":{"id":"ziTpmjh_7I25","executionInfo":{"status":"ok","timestamp":1787474391750,"user_tz":-330,"elapsed":20,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":3,"outputs":[]},{"cell_type":"code","source":[],"metadata":{"id":"qsuWozrTMP4R","executionInfo":{"status":"ok","timestamp":1787474391763,"user_tz":-330,"elapsed":12,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":3,"outputs":[]},{"cell_type":"code","source":["import numpy as np\n","import matplotlib.pyplot as plt\n","import seaborn as sns\n","from sklearn.metrics import classification_report, confusion_matrix, roc_curve, auc\n","from sklearn.preprocessing import label_binarize\n","from tensorflow.keras.models import load_model"],"metadata":{"id":"nxAAPGa757Ex","executionInfo":{"status":"ok","timestamp":1787474392968,"user_tz":-330,"elapsed":1194,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":4,"outputs":[]},{"cell_type":"code","source":[],"metadata":{"id":"yqVnKH849X3f","executionInfo":{"status":"ok","timestamp":1787474392977,"user_tz":-330,"elapsed":7,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":4,"outputs":[]},{"cell_type":"code","source":["print(\"GPU:\", tf.config.list_physical_devices('GPU'))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"t2yKNLVc55Z4","executionInfo":{"status":"ok","timestamp":1787474394626,"user_tz":-330,"elapsed":1648,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"997827d4-8daa-4010-9fdc-e5edaae31621"},"execution_count":5,"outputs":[{"output_type":"stream","name":"stdout","text":["GPU: [PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]\n"]}]},{"cell_type":"code","execution_count":6,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"J3yE0IytKG1c","executionInfo":{"status":"ok","timestamp":1787474410027,"user_tz":-330,"elapsed":15399,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"d1b3e6d5-7d79-40f6-b789-457b853465e6"},"outputs":[{"output_type":"stream","name":"stdout","text":["Mounted at /content/drive\n"]}],"source":["from google.colab import drive\n","drive.mount('/content/drive')"]},{"cell_type":"code","source":["train_dir = '/content/drive/MyDrive/cancer-cnn/extracted data/Training'\n","test_dir = '/content/drive/MyDrive/cancer-cnn/extracted data/Testing'"],"metadata":{"id":"ZoFscuOz6Jv8","executionInfo":{"status":"ok","timestamp":1787474410030,"user_tz":-330,"elapsed":2,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":7,"outputs":[]},{"cell_type":"code","source":[],"metadata":{"id":"UrsAzHg66PfS","executionInfo":{"status":"ok","timestamp":1787462030811,"user_tz":-330,"elapsed":204,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":22,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"r2cZxSxzMgSd"},"source":["**preprocessing img**"]},{"cell_type":"code","source":["#img Augmentation fun\n","def augment_image(image):\n","    image = Image.fromarray(np.uint8(image))\n","    image = ImageEnhance.Brightness(image).enhance(random.uniform(0.8, 1.2))#brightness -random\n","    image = ImageEnhance.Contrast(image).enhance(random.uniform(0.8, 1.2))  #contrast -random\n","    image = np.array(image) / 255.0                                         #normalize pixel values to [0, 1]\n","    return image\n","\n","#load img & apply augmentation\n","def open_images(paths):\n","    images = []\n","    for path in paths:\n","        image = load_img(path, target_size=(IMAGE_SIZE, IMAGE_SIZE))\n","        image = augment_image(image)\n","        images.append(image)\n","    return np.array(images)\n","\n","#encoding labels (label names)\n","def encode_label(labels):\n","    unique_labels = os.listdir(train_dir)  # Ensure unique labels are determined\n","    encoded = [unique_labels.index(label) for label in labels]\n","    return np.array(encoded)\n","\n","#data generator for batching\n","def datagen(paths, labels, batch_size=12, epochs=1):\n","    for _ in range(epochs):\n","        for i in range(0, len(paths), batch_size):\n","            batch_paths = paths[i:i + batch_size]\n","            batch_images = open_images(batch_paths)    #open & augment img\n","            batch_labels = labels[i:i + batch_size]\n","            batch_labels = encode_label(batch_labels)  # encode labels\n","            yield batch_images, batch_labels           #yield the batch\n","\n"],"metadata":{"id":"fpQW8CvY9OZQ","executionInfo":{"status":"ok","timestamp":1787475543850,"user_tz":-330,"elapsed":2,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":25,"outputs":[]},{"cell_type":"code","source":[],"metadata":{"id":"NEyd1bjLKnZx","executionInfo":{"status":"ok","timestamp":1787462034952,"user_tz":-330,"elapsed":40,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":23,"outputs":[]},{"cell_type":"code","source":["# FIXED CLASS ORDER\n","class_names = [\n","    \"pituitary\",\n","    \"notumor\",\n","    \"meningioma\",\n","    \"glioma\"\n","]\n","\n","print(\"Class mapping:\")\n","for i, name in enumerate(class_names):\n","    print(f\"{i} → {name}\")\n","\n","\n","# TRAIN DATA\n","train_paths = []\n","train_labels = []\n","\n","# Use our fixed class order, NOT os.listdir() order\n","for label in class_names:\n","    for image in os.listdir(os.path.join(train_dir, label)):\n","        train_paths.append(\n","            os.path.join(train_dir, label, image)\n","        )\n","        train_labels.append(label)\n","\n","train_paths, train_labels = shuffle(\n","    train_paths,\n","    train_labels,\n","    random_state=42\n",")\n","\n","\n","# CREATE VALIDATION SET\n","from sklearn.model_selection import train_test_split\n","\n","train_paths, val_paths, train_labels, val_labels = train_test_split(\n","    train_paths,\n","    train_labels,\n","    test_size=0.15,\n","    random_state=42,\n","    stratify=train_labels\n",")\n","\n","\n","# TEST DATA\n","test_paths = []\n","test_labels = []\n","\n","# Use the SAME fixed class order\n","for label in class_names:\n","    for image in os.listdir(os.path.join(test_dir, label)):\n","        test_paths.append(\n","            os.path.join(test_dir, label, image)\n","        )\n","        test_labels.append(label)\n","\n","test_paths, test_labels = shuffle(\n","    test_paths,\n","    test_labels,\n","    random_state=42\n",")\n","\n","\n","# LABEL ENCODING\n","def encode_label(labels):\n","    encoded = [\n","        class_names.index(label)\n","        for label in labels\n","    ]\n","\n","    return np.array(encoded)"],"metadata":{"id":"L4XDljU4NnUS","executionInfo":{"status":"ok","timestamp":1787475555419,"user_tz":-330,"elapsed":181,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"colab":{"base_uri":"https://localhost:8080/"},"outputId":"aaeb45e2-3f77-489e-fd68-5a0d71a9eca7"},"execution_count":26,"outputs":[{"output_type":"stream","name":"stdout","text":["Class mapping:\n","0 → pituitary\n","1 → notumor\n","2 → meningioma\n","3 → glioma\n"]}]},{"cell_type":"code","source":["print(class_names)\n","print(encode_label(class_names))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"GimB_ISWvl25","executionInfo":{"status":"ok","timestamp":1787475564376,"user_tz":-330,"elapsed":100,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"53cf8f5f-8fd9-4a96-fd79-195ef34681f1"},"execution_count":27,"outputs":[{"output_type":"stream","name":"stdout","text":["['pituitary', 'notumor', 'meningioma', 'glioma']\n","[0 1 2 3]\n"]}]},{"cell_type":"code","source":["from sklearn.model_selection import train_test_split\n","\n","train_paths, val_paths, train_labels, val_labels = train_test_split(\n","    train_paths,\n","    train_labels,\n","    test_size=0.15,\n","    random_state=42,\n","    stratify=train_labels\n",")"],"metadata":{"id":"Uxq6eYo_NjQK","executionInfo":{"status":"ok","timestamp":1787475564624,"user_tz":-330,"elapsed":18,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":28,"outputs":[]},{"cell_type":"code","source":[],"metadata":{"id":"mQ7OaRWYo89l","executionInfo":{"status":"ok","timestamp":1787462038918,"user_tz":-330,"elapsed":3,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":26,"outputs":[]},{"cell_type":"markdown","source":["# **Training of the model with first set of parameters**"],"metadata":{"id":"X3_kke9wKpkO"}},{"cell_type":"code","source":[],"metadata":{"id":"r5juY9eOs4Tm"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["IMAGE_SIZE = 128\n","NUM_CLASSES = 4\n","\n","\n","# Load pretrained DenseNet121\n","base_model = DenseNet121(\n","    input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3),\n","    include_top=False,\n","    weights='imagenet'\n",")\n","\n","\n","# Freeze the complete DenseNet121 backbone\n","for layer in base_model.layers:\n","    layer.trainable = False\n","\n","\n","# Classification head\n","model = Sequential()\n","\n","model.add(Input(shape=(IMAGE_SIZE, IMAGE_SIZE, 3)))\n","\n","model.add(base_model)\n","\n","model.add(GlobalAveragePooling2D())\n","\n","model.add(Dense(256, activation='relu'))\n","model.add(BatchNormalization())\n","model.add(Dropout(0.4))\n","\n","model.add(Dense(128, activation='relu'))\n","model.add(BatchNormalization())\n","model.add(Dropout(0.3))\n","\n","model.add(Dense(NUM_CLASSES, activation='softmax'))\n","\n","\n","# Compile\n","model.compile(\n","    optimizer=Adam(learning_rate=1e-4),\n","    loss='sparse_categorical_crossentropy',\n","    metrics=['sparse_categorical_accuracy']\n",")\n","\n","model.summary()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":520},"id":"qo5v50EwKnOv","executionInfo":{"status":"ok","timestamp":1787462158515,"user_tz":-330,"elapsed":4906,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"0fdaf47e-c533-42dc-a13e-a4c1140a6a9c"},"execution_count":28,"outputs":[{"output_type":"stream","name":"stdout","text":["Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/densenet/densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5\n","\u001b[1m29084464/29084464\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0us/step\n"]},{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential\"\u001b[0m\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ densenet121 (\u001b[38;5;33mFunctional\u001b[0m)        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m1024\u001b[0m)     │     \u001b[38;5;34m7,037,504\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ global_average_pooling2d        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1024\u001b[0m)           │             \u001b[38;5;34m0\u001b[0m │\n","│ (\u001b[38;5;33mGlobalAveragePooling2D\u001b[0m)        │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │       \u001b[38;5;34m262,400\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │         \u001b[38;5;34m1,024\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │        \u001b[38;5;34m32,896\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_1           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │           \u001b[38;5;34m512\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m)              │           \u001b[38;5;34m516\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ densenet121 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Functional</span>)        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1024</span>)     │     <span style=\"color: #00af00; text-decoration-color: #00af00\">7,037,504</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ global_average_pooling2d        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1024</span>)           │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">GlobalAveragePooling2D</span>)        │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │       <span style=\"color: #00af00; text-decoration-color: #00af00\">262,400</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,024</span> │\n","│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">32,896</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_1           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │           <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> │\n","│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">516</span> │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m7,334,852\u001b[0m (27.98 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">7,334,852</span> (27.98 MB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m296,580\u001b[0m (1.13 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">296,580</span> (1.13 MB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m7,038,272\u001b[0m (26.85 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">7,038,272</span> (26.85 MB)\n","</pre>\n"]},"metadata":{}}]},{"cell_type":"code","source":["# DENSENET121 - STAGE 1 TRAINING\n","\n","batch_size = 20\n","epochs = 20\n","\n","steps = len(train_paths) // batch_size\n","\n","\n","# Early stopping\n","early_stopping = tf.keras.callbacks.EarlyStopping(\n","    monitor='val_loss',\n","    patience=5,\n","    restore_best_weights=True,\n","    verbose=1\n",")\n","\n","\n","# Reduce learning rate when validation loss stops improving\n","reduce_lr = tf.keras.callbacks.ReduceLROnPlateau(\n","    monitor='val_loss',\n","    factor=0.2,\n","    patience=2,\n","    min_lr=1e-7,\n","    verbose=1\n",")\n","\n","\n","# Model checkpoint\n","checkpoint = tf.keras.callbacks.ModelCheckpoint(\n","    'densenet121_stage1_best.keras',\n","    monitor='val_loss',\n","    save_best_only=True,\n","    verbose=1\n",")"],"metadata":{"id":"Z4-uiyDlKnUm","executionInfo":{"status":"ok","timestamp":1787462173964,"user_tz":-330,"elapsed":3,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":29,"outputs":[]},{"cell_type":"code","source":["# Train\n","history = model.fit(\n","    datagen(\n","        train_paths,\n","        train_labels,\n","        batch_size=batch_size,\n","        epochs=epochs\n","    ),\n","\n","    epochs=epochs,\n","\n","    steps_per_epoch=steps,\n","\n","    validation_data=datagen(\n","        val_paths,\n","        val_labels,\n","        batch_size=batch_size,\n","        epochs=1\n","    ),\n","\n","    validation_steps=len(val_paths) // batch_size,\n","\n","    callbacks=[\n","        early_stopping,\n","        reduce_lr,\n","        checkpoint\n","    ]\n",")"],"metadata":{"id":"CPof__kiNy-j","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1787464245117,"user_tz":-330,"elapsed":2001542,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"2021d23e-9cac-4fa9-d58c-f952aa20b2a6"},"execution_count":30,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7s/step - loss: 1.4531 - sparse_categorical_accuracy: 0.4511\n","Epoch 1: val_loss improved from None to 0.52277, saving model to densenet121_stage1_best.keras\n","\n","Epoch 1: finished saving model to densenet121_stage1_best.keras\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1712s\u001b[0m 8s/step - loss: 1.1374 - sparse_categorical_accuracy: 0.5658 - val_loss: 0.5228 - val_sparse_categorical_accuracy: 0.7986 - learning_rate: 1.0000e-04\n","Epoch 2/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 85ms/step - loss: 0.7387 - sparse_categorical_accuracy: 0.7318\n","Epoch 2: val_loss did not improve from 0.52277\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m31s\u001b[0m 85ms/step - loss: 0.6950 - sparse_categorical_accuracy: 0.7444 - val_loss: 0.5693 - val_sparse_categorical_accuracy: 0.8000 - learning_rate: 1.0000e-04\n","Epoch 3/20\n","\u001b[1m  3/202\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m6s\u001b[0m 33ms/step - loss: 0.6780 - sparse_categorical_accuracy: 0.8647"]},{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.13/dist-packages/keras/src/trainers/epoch_iterator.py:164: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches. You may need to use the `.repeat()` function when building your dataset.\n","  self._interrupted_warning()\n"]},{"output_type":"stream","name":"stdout","text":["\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 90ms/step - loss: 0.6190 - sparse_categorical_accuracy: 0.7752\n","Epoch 3: ReduceLROnPlateau reducing learning rate to 1.9999999494757503e-05.\n","\n","Epoch 3: val_loss did not improve from 0.52277\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 91ms/step - loss: 0.5865 - sparse_categorical_accuracy: 0.7842 - val_loss: 0.5368 - val_sparse_categorical_accuracy: 0.8250 - learning_rate: 1.0000e-04\n","Epoch 4/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 91ms/step - loss: 0.5368 - sparse_categorical_accuracy: 0.8081\n","Epoch 4: val_loss did not improve from 0.52277\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 92ms/step - loss: 0.5150 - sparse_categorical_accuracy: 0.8110 - val_loss: 0.5236 - val_sparse_categorical_accuracy: 0.8250 - learning_rate: 2.0000e-05\n","Epoch 5/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 86ms/step - loss: 0.5011 - sparse_categorical_accuracy: 0.8062\n","Epoch 5: val_loss improved from 0.52277 to 0.50979, saving model to densenet121_stage1_best.keras\n","\n","Epoch 5: finished saving model to densenet121_stage1_best.keras\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 94ms/step - loss: 0.4968 - sparse_categorical_accuracy: 0.8127 - val_loss: 0.5098 - val_sparse_categorical_accuracy: 0.8250 - learning_rate: 2.0000e-05\n","Epoch 6/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 87ms/step - loss: 0.4987 - sparse_categorical_accuracy: 0.8178\n","Epoch 6: val_loss did not improve from 0.50979\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 88ms/step - loss: 0.4886 - sparse_categorical_accuracy: 0.8179 - val_loss: 0.5119 - val_sparse_categorical_accuracy: 0.8250 - learning_rate: 2.0000e-05\n","Epoch 7/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 90ms/step - loss: 0.5063 - sparse_categorical_accuracy: 0.8189\n","Epoch 7: val_loss improved from 0.50979 to 0.49504, saving model to densenet121_stage1_best.keras\n","\n","Epoch 7: finished saving model to densenet121_stage1_best.keras\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 99ms/step - loss: 0.4844 - sparse_categorical_accuracy: 0.8271 - val_loss: 0.4950 - val_sparse_categorical_accuracy: 0.8250 - learning_rate: 2.0000e-05\n","Epoch 8/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 86ms/step - loss: 0.4909 - sparse_categorical_accuracy: 0.8206\n","Epoch 8: val_loss improved from 0.49504 to 0.48299, saving model to densenet121_stage1_best.keras\n","\n","Epoch 8: finished saving model to densenet121_stage1_best.keras\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 98ms/step - loss: 0.4752 - sparse_categorical_accuracy: 0.8246 - val_loss: 0.4830 - val_sparse_categorical_accuracy: 0.8250 - learning_rate: 2.0000e-05\n","Epoch 9/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 83ms/step - loss: 0.4636 - sparse_categorical_accuracy: 0.8182\n","Epoch 9: val_loss did not improve from 0.48299\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m17s\u001b[0m 84ms/step - loss: 0.4446 - sparse_categorical_accuracy: 0.8343 - val_loss: 0.4864 - val_sparse_categorical_accuracy: 0.8500 - learning_rate: 2.0000e-05\n","Epoch 10/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 93ms/step - loss: 0.4522 - sparse_categorical_accuracy: 0.8343\n","Epoch 10: val_loss improved from 0.48299 to 0.46364, saving model to densenet121_stage1_best.keras\n","\n","Epoch 10: finished saving model to densenet121_stage1_best.keras\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 106ms/step - loss: 0.4477 - sparse_categorical_accuracy: 0.8383 - val_loss: 0.4636 - val_sparse_categorical_accuracy: 0.8500 - learning_rate: 2.0000e-05\n","Epoch 11/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 79ms/step - loss: 0.4220 - sparse_categorical_accuracy: 0.8284\n","Epoch 11: val_loss did not improve from 0.46364\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m16s\u001b[0m 79ms/step - loss: 0.4192 - sparse_categorical_accuracy: 0.8383 - val_loss: 0.4696 - val_sparse_categorical_accuracy: 0.8750 - learning_rate: 2.0000e-05\n","Epoch 12/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 85ms/step - loss: 0.4498 - sparse_categorical_accuracy: 0.8316\n","Epoch 12: ReduceLROnPlateau reducing learning rate to 3.999999898951501e-06.\n","\n","Epoch 12: val_loss did not improve from 0.46364\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m17s\u001b[0m 86ms/step - loss: 0.4326 - sparse_categorical_accuracy: 0.8348 - val_loss: 0.4642 - val_sparse_categorical_accuracy: 0.8750 - learning_rate: 2.0000e-05\n","Epoch 13/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 88ms/step - loss: 0.4280 - sparse_categorical_accuracy: 0.8471\n","Epoch 13: val_loss did not improve from 0.46364\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 90ms/step - loss: 0.4122 - sparse_categorical_accuracy: 0.8467 - val_loss: 0.4644 - val_sparse_categorical_accuracy: 0.8500 - learning_rate: 4.0000e-06\n","Epoch 14/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 87ms/step - loss: 0.4280 - sparse_categorical_accuracy: 0.8453\n","Epoch 14: ReduceLROnPlateau reducing learning rate to 7.999999979801942e-07.\n","\n","Epoch 14: val_loss did not improve from 0.46364\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 87ms/step - loss: 0.4228 - sparse_categorical_accuracy: 0.8475 - val_loss: 0.4650 - val_sparse_categorical_accuracy: 0.8750 - learning_rate: 4.0000e-06\n","Epoch 15/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 86ms/step - loss: 0.4143 - sparse_categorical_accuracy: 0.8496\n","Epoch 15: val_loss did not improve from 0.46364\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m17s\u001b[0m 87ms/step - loss: 0.4197 - sparse_categorical_accuracy: 0.8487 - val_loss: 0.4650 - val_sparse_categorical_accuracy: 0.8750 - learning_rate: 8.0000e-07\n","Epoch 15: early stopping\n","Restoring model weights from the end of the best epoch: 10.\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"oE66ONSKDW9k"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["print(\"Best validation accuracy:\")\n","print(max(history.history['val_sparse_categorical_accuracy']))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Ig4JaLoGXLxw","executionInfo":{"status":"ok","timestamp":1787464245389,"user_tz":-330,"elapsed":18,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"66161b39-14cb-4b0d-bac8-9f93cd784ada"},"execution_count":31,"outputs":[{"output_type":"stream","name":"stdout","text":["Best validation accuracy:\n","0.875\n"]}]},{"cell_type":"code","source":["print(\"Best validation loss:\")\n","print(min(history.history['val_loss']))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"TXBzbim0XPyn","executionInfo":{"status":"ok","timestamp":1787464245396,"user_tz":-330,"elapsed":14,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"ca3948a4-0a6c-4af4-9b48-40b165e986ea"},"execution_count":32,"outputs":[{"output_type":"stream","name":"stdout","text":["Best validation loss:\n","0.4636387228965759\n"]}]},{"cell_type":"code","source":["plt.figure(figsize=(10,5))\n","plt.grid(True)\n","plt.plot(history.history['sparse_categorical_accuracy'], '.g-', linewidth=2)\n","plt.plot(history.history['loss'], '.r-', linewidth=2.5)\n","plt.title('Model Training History')\n","plt.xlabel('Epoch')\n","plt.ylabel('Value')\n","plt.xticks([x for x in range(epochs)])\n","plt.legend(['accuracy', 'loss'], loc='upper left', bbox_to_anchor=(1, 1))\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":487},"id":"NoGrm8BxWI_X","executionInfo":{"status":"ok","timestamp":1787464245489,"user_tz":-330,"elapsed":93,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"963ab8c0-6ab4-41d2-a022-d9a7d616babd"},"execution_count":33,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 1000x500 with 1 Axes>"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"code","source":["import matplotlib.pyplot as plt\n","\n","plt.plot(history.history['sparse_categorical_accuracy'], label='Training')\n","plt.plot(history.history['val_sparse_categorical_accuracy'], label='Validation')\n","\n","plt.xlabel('Epoch')\n","plt.ylabel('Accuracy')\n","plt.legend()\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":449},"id":"H5uHADMeXVUh","executionInfo":{"status":"ok","timestamp":1787464245573,"user_tz":-330,"elapsed":83,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"be0b186b-824e-4b54-dbf7-864c2bf90035"},"execution_count":34,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"code","source":[],"metadata":{"id":"skRQtWRQVy2d","executionInfo":{"status":"ok","timestamp":1787464245593,"user_tz":-330,"elapsed":2,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":34,"outputs":[]},{"cell_type":"code","source":["test_images = open_images(test_paths)            #load and augment test images\n","test_labels_encoded = encode_label(test_labels)  # encode the test labels\n","#Predict on test data"],"metadata":{"id":"C9Al8JIrXxsb","executionInfo":{"status":"ok","timestamp":1787464691808,"user_tz":-330,"elapsed":446214,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":35,"outputs":[]},{"cell_type":"code","source":["test_predictions = model.predict(test_images)\n","#predict using the trained model"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"PQ1XNQt1XyZL","executionInfo":{"status":"ok","timestamp":1787464708009,"user_tz":-330,"elapsed":16199,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"1d436a84-4c0c-4c0d-842e-2eb516cd6ff9"},"execution_count":36,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m15s\u001b[0m 32ms/step\n"]}]},{"cell_type":"code","source":["print(classification_report(test_labels_encoded, np.argmax(test_predictions, axis=1)))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Ksy834n4YDX-","executionInfo":{"status":"ok","timestamp":1787464708034,"user_tz":-330,"elapsed":24,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"546bee53-3998-48d9-ac2b-84d1a9e28164"},"execution_count":37,"outputs":[{"output_type":"stream","name":"stdout","text":["              precision    recall  f1-score   support\n","\n","           0       0.84      0.95      0.89       400\n","           1       0.82      0.98      0.89       400\n","           2       0.78      0.70      0.74       400\n","           3       0.86      0.67      0.76       400\n","\n","    accuracy                           0.83      1600\n","   macro avg       0.83      0.83      0.82      1600\n","weighted avg       0.83      0.83      0.82      1600\n","\n"]}]},{"cell_type":"code","source":["conf_matrix = confusion_matrix(test_labels_encoded, np.argmax(test_predictions, axis=1))\n","print(conf_matrix)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"GB4e4zE0YDNl","executionInfo":{"status":"ok","timestamp":1787464708084,"user_tz":-330,"elapsed":48,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"62bdb082-b253-4da1-8a48-9046a2b454a1"},"execution_count":38,"outputs":[{"output_type":"stream","name":"stdout","text":["[[381   2  12   5]\n"," [  1 392   5   2]\n"," [ 48  38 279  35]\n"," [ 22  46  63 269]]\n"]}]},{"cell_type":"markdown","source":["# **Stage 2 fine-tuning**"],"metadata":{"id":"bRRjOC6rOKP4"}},{"cell_type":"code","source":["# STAGE 2 - FINE TUNING DENSENET121\n","\n","# Freeze everything first\n","for layer in base_model.layers:\n","    layer.trainable = False\n","\n","\n","# Unfreeze DenseNet121's final dense block\n","set_trainable = False\n","\n","for layer in base_model.layers:\n","\n","    if layer.name == 'conv5_block1_0_bn':\n","        set_trainable = True\n","\n","    if set_trainable:\n","        layer.trainable = True\n","\n","\n","# Check which layers are trainable\n","print(\"\\nTrainable DenseNet121 layers:\")\n","\n","for layer in base_model.layers:\n","    print(layer.name, layer.trainable)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"yDDIItDxOJR_","executionInfo":{"status":"ok","timestamp":1787464708096,"user_tz":-330,"elapsed":10,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"f7fcc6fe-2724-4fbf-b231-65d071293f36"},"execution_count":39,"outputs":[{"output_type":"stream","name":"stdout","text":["\n","Trainable DenseNet121 layers:\n","input_layer False\n","zero_padding2d False\n","conv1_conv False\n","conv1_bn False\n","conv1_relu False\n","zero_padding2d_1 False\n","pool1 False\n","conv2_block1_0_bn False\n","conv2_block1_0_relu False\n","conv2_block1_1_conv False\n","conv2_block1_1_bn False\n","conv2_block1_1_relu False\n","conv2_block1_2_conv False\n","conv2_block1_concat False\n","conv2_block2_0_bn False\n","conv2_block2_0_relu False\n","conv2_block2_1_conv False\n","conv2_block2_1_bn False\n","conv2_block2_1_relu False\n","conv2_block2_2_conv False\n","conv2_block2_concat False\n","conv2_block3_0_bn False\n","conv2_block3_0_relu False\n","conv2_block3_1_conv False\n","conv2_block3_1_bn False\n","conv2_block3_1_relu False\n","conv2_block3_2_conv False\n","conv2_block3_concat False\n","conv2_block4_0_bn False\n","conv2_block4_0_relu False\n","conv2_block4_1_conv False\n","conv2_block4_1_bn False\n","conv2_block4_1_relu False\n","conv2_block4_2_conv False\n","conv2_block4_concat False\n","conv2_block5_0_bn False\n","conv2_block5_0_relu False\n","conv2_block5_1_conv False\n","conv2_block5_1_bn False\n","conv2_block5_1_relu False\n","conv2_block5_2_conv False\n","conv2_block5_concat False\n","conv2_block6_0_bn False\n","conv2_block6_0_relu False\n","conv2_block6_1_conv False\n","conv2_block6_1_bn False\n","conv2_block6_1_relu False\n","conv2_block6_2_conv False\n","conv2_block6_concat False\n","pool2_bn False\n","pool2_relu False\n","pool2_conv False\n","pool2_pool False\n","conv3_block1_0_bn False\n","conv3_block1_0_relu False\n","conv3_block1_1_conv False\n","conv3_block1_1_bn False\n","conv3_block1_1_relu False\n","conv3_block1_2_conv False\n","conv3_block1_concat False\n","conv3_block2_0_bn False\n","conv3_block2_0_relu False\n","conv3_block2_1_conv False\n","conv3_block2_1_bn False\n","conv3_block2_1_relu False\n","conv3_block2_2_conv False\n","conv3_block2_concat False\n","conv3_block3_0_bn False\n","conv3_block3_0_relu False\n","conv3_block3_1_conv False\n","conv3_block3_1_bn False\n","conv3_block3_1_relu False\n","conv3_block3_2_conv False\n","conv3_block3_concat False\n","conv3_block4_0_bn False\n","conv3_block4_0_relu False\n","conv3_block4_1_conv False\n","conv3_block4_1_bn False\n","conv3_block4_1_relu False\n","conv3_block4_2_conv False\n","conv3_block4_concat False\n","conv3_block5_0_bn False\n","conv3_block5_0_relu False\n","conv3_block5_1_conv False\n","conv3_block5_1_bn False\n","conv3_block5_1_relu False\n","conv3_block5_2_conv False\n","conv3_block5_concat False\n","conv3_block6_0_bn False\n","conv3_block6_0_relu False\n","conv3_block6_1_conv False\n","conv3_block6_1_bn False\n","conv3_block6_1_relu False\n","conv3_block6_2_conv False\n","conv3_block6_concat False\n","conv3_block7_0_bn False\n","conv3_block7_0_relu False\n","conv3_block7_1_conv False\n","conv3_block7_1_bn False\n","conv3_block7_1_relu False\n","conv3_block7_2_conv False\n","conv3_block7_concat False\n","conv3_block8_0_bn False\n","conv3_block8_0_relu False\n","conv3_block8_1_conv False\n","conv3_block8_1_bn False\n","conv3_block8_1_relu False\n","conv3_block8_2_conv False\n","conv3_block8_concat False\n","conv3_block9_0_bn False\n","conv3_block9_0_relu False\n","conv3_block9_1_conv False\n","conv3_block9_1_bn False\n","conv3_block9_1_relu False\n","conv3_block9_2_conv False\n","conv3_block9_concat False\n","conv3_block10_0_bn False\n","conv3_block10_0_relu False\n","conv3_block10_1_conv False\n","conv3_block10_1_bn False\n","conv3_block10_1_relu False\n","conv3_block10_2_conv False\n","conv3_block10_concat False\n","conv3_block11_0_bn False\n","conv3_block11_0_relu False\n","conv3_block11_1_conv False\n","conv3_block11_1_bn False\n","conv3_block11_1_relu False\n","conv3_block11_2_conv False\n","conv3_block11_concat False\n","conv3_block12_0_bn False\n","conv3_block12_0_relu False\n","conv3_block12_1_conv False\n","conv3_block12_1_bn False\n","conv3_block12_1_relu False\n","conv3_block12_2_conv False\n","conv3_block12_concat False\n","pool3_bn False\n","pool3_relu False\n","pool3_conv False\n","pool3_pool False\n","conv4_block1_0_bn False\n","conv4_block1_0_relu False\n","conv4_block1_1_conv False\n","conv4_block1_1_bn False\n","conv4_block1_1_relu False\n","conv4_block1_2_conv False\n","conv4_block1_concat False\n","conv4_block2_0_bn False\n","conv4_block2_0_relu False\n","conv4_block2_1_conv False\n","conv4_block2_1_bn False\n","conv4_block2_1_relu False\n","conv4_block2_2_conv False\n","conv4_block2_concat False\n","conv4_block3_0_bn False\n","conv4_block3_0_relu False\n","conv4_block3_1_conv False\n","conv4_block3_1_bn False\n","conv4_block3_1_relu False\n","conv4_block3_2_conv False\n","conv4_block3_concat False\n","conv4_block4_0_bn False\n","conv4_block4_0_relu False\n","conv4_block4_1_conv False\n","conv4_block4_1_bn False\n","conv4_block4_1_relu False\n","conv4_block4_2_conv False\n","conv4_block4_concat False\n","conv4_block5_0_bn False\n","conv4_block5_0_relu False\n","conv4_block5_1_conv False\n","conv4_block5_1_bn False\n","conv4_block5_1_relu False\n","conv4_block5_2_conv False\n","conv4_block5_concat False\n","conv4_block6_0_bn False\n","conv4_block6_0_relu False\n","conv4_block6_1_conv False\n","conv4_block6_1_bn False\n","conv4_block6_1_relu False\n","conv4_block6_2_conv False\n","conv4_block6_concat False\n","conv4_block7_0_bn False\n","conv4_block7_0_relu False\n","conv4_block7_1_conv False\n","conv4_block7_1_bn False\n","conv4_block7_1_relu False\n","conv4_block7_2_conv False\n","conv4_block7_concat False\n","conv4_block8_0_bn False\n","conv4_block8_0_relu False\n","conv4_block8_1_conv False\n","conv4_block8_1_bn False\n","conv4_block8_1_relu False\n","conv4_block8_2_conv False\n","conv4_block8_concat False\n","conv4_block9_0_bn False\n","conv4_block9_0_relu False\n","conv4_block9_1_conv False\n","conv4_block9_1_bn False\n","conv4_block9_1_relu False\n","conv4_block9_2_conv False\n","conv4_block9_concat False\n","conv4_block10_0_bn False\n","conv4_block10_0_relu False\n","conv4_block10_1_conv False\n","conv4_block10_1_bn False\n","conv4_block10_1_relu False\n","conv4_block10_2_conv False\n","conv4_block10_concat False\n","conv4_block11_0_bn False\n","conv4_block11_0_relu False\n","conv4_block11_1_conv False\n","conv4_block11_1_bn False\n","conv4_block11_1_relu False\n","conv4_block11_2_conv False\n","conv4_block11_concat False\n","conv4_block12_0_bn False\n","conv4_block12_0_relu False\n","conv4_block12_1_conv False\n","conv4_block12_1_bn False\n","conv4_block12_1_relu False\n","conv4_block12_2_conv False\n","conv4_block12_concat False\n","conv4_block13_0_bn False\n","conv4_block13_0_relu False\n","conv4_block13_1_conv False\n","conv4_block13_1_bn False\n","conv4_block13_1_relu False\n","conv4_block13_2_conv False\n","conv4_block13_concat False\n","conv4_block14_0_bn False\n","conv4_block14_0_relu False\n","conv4_block14_1_conv False\n","conv4_block14_1_bn False\n","conv4_block14_1_relu False\n","conv4_block14_2_conv False\n","conv4_block14_concat False\n","conv4_block15_0_bn False\n","conv4_block15_0_relu False\n","conv4_block15_1_conv False\n","conv4_block15_1_bn False\n","conv4_block15_1_relu False\n","conv4_block15_2_conv False\n","conv4_block15_concat False\n","conv4_block16_0_bn False\n","conv4_block16_0_relu False\n","conv4_block16_1_conv False\n","conv4_block16_1_bn False\n","conv4_block16_1_relu False\n","conv4_block16_2_conv False\n","conv4_block16_concat False\n","conv4_block17_0_bn False\n","conv4_block17_0_relu False\n","conv4_block17_1_conv False\n","conv4_block17_1_bn False\n","conv4_block17_1_relu False\n","conv4_block17_2_conv False\n","conv4_block17_concat False\n","conv4_block18_0_bn False\n","conv4_block18_0_relu False\n","conv4_block18_1_conv False\n","conv4_block18_1_bn False\n","conv4_block18_1_relu False\n","conv4_block18_2_conv False\n","conv4_block18_concat False\n","conv4_block19_0_bn False\n","conv4_block19_0_relu False\n","conv4_block19_1_conv False\n","conv4_block19_1_bn False\n","conv4_block19_1_relu False\n","conv4_block19_2_conv False\n","conv4_block19_concat False\n","conv4_block20_0_bn False\n","conv4_block20_0_relu False\n","conv4_block20_1_conv False\n","conv4_block20_1_bn False\n","conv4_block20_1_relu False\n","conv4_block20_2_conv False\n","conv4_block20_concat False\n","conv4_block21_0_bn False\n","conv4_block21_0_relu False\n","conv4_block21_1_conv False\n","conv4_block21_1_bn False\n","conv4_block21_1_relu False\n","conv4_block21_2_conv False\n","conv4_block21_concat False\n","conv4_block22_0_bn False\n","conv4_block22_0_relu False\n","conv4_block22_1_conv False\n","conv4_block22_1_bn False\n","conv4_block22_1_relu False\n","conv4_block22_2_conv False\n","conv4_block22_concat False\n","conv4_block23_0_bn False\n","conv4_block23_0_relu False\n","conv4_block23_1_conv False\n","conv4_block23_1_bn False\n","conv4_block23_1_relu False\n","conv4_block23_2_conv False\n","conv4_block23_concat False\n","conv4_block24_0_bn False\n","conv4_block24_0_relu False\n","conv4_block24_1_conv False\n","conv4_block24_1_bn False\n","conv4_block24_1_relu False\n","conv4_block24_2_conv False\n","conv4_block24_concat False\n","pool4_bn False\n","pool4_relu False\n","pool4_conv False\n","pool4_pool False\n","conv5_block1_0_bn True\n","conv5_block1_0_relu True\n","conv5_block1_1_conv True\n","conv5_block1_1_bn True\n","conv5_block1_1_relu True\n","conv5_block1_2_conv True\n","conv5_block1_concat True\n","conv5_block2_0_bn True\n","conv5_block2_0_relu True\n","conv5_block2_1_conv True\n","conv5_block2_1_bn True\n","conv5_block2_1_relu True\n","conv5_block2_2_conv True\n","conv5_block2_concat True\n","conv5_block3_0_bn True\n","conv5_block3_0_relu True\n","conv5_block3_1_conv True\n","conv5_block3_1_bn True\n","conv5_block3_1_relu True\n","conv5_block3_2_conv True\n","conv5_block3_concat True\n","conv5_block4_0_bn True\n","conv5_block4_0_relu True\n","conv5_block4_1_conv True\n","conv5_block4_1_bn True\n","conv5_block4_1_relu True\n","conv5_block4_2_conv True\n","conv5_block4_concat True\n","conv5_block5_0_bn True\n","conv5_block5_0_relu True\n","conv5_block5_1_conv True\n","conv5_block5_1_bn True\n","conv5_block5_1_relu True\n","conv5_block5_2_conv True\n","conv5_block5_concat True\n","conv5_block6_0_bn True\n","conv5_block6_0_relu True\n","conv5_block6_1_conv True\n","conv5_block6_1_bn True\n","conv5_block6_1_relu True\n","conv5_block6_2_conv True\n","conv5_block6_concat True\n","conv5_block7_0_bn True\n","conv5_block7_0_relu True\n","conv5_block7_1_conv True\n","conv5_block7_1_bn True\n","conv5_block7_1_relu True\n","conv5_block7_2_conv True\n","conv5_block7_concat True\n","conv5_block8_0_bn True\n","conv5_block8_0_relu True\n","conv5_block8_1_conv True\n","conv5_block8_1_bn True\n","conv5_block8_1_relu True\n","conv5_block8_2_conv True\n","conv5_block8_concat True\n","conv5_block9_0_bn True\n","conv5_block9_0_relu True\n","conv5_block9_1_conv True\n","conv5_block9_1_bn True\n","conv5_block9_1_relu True\n","conv5_block9_2_conv True\n","conv5_block9_concat True\n","conv5_block10_0_bn True\n","conv5_block10_0_relu True\n","conv5_block10_1_conv True\n","conv5_block10_1_bn True\n","conv5_block10_1_relu True\n","conv5_block10_2_conv True\n","conv5_block10_concat True\n","conv5_block11_0_bn True\n","conv5_block11_0_relu True\n","conv5_block11_1_conv True\n","conv5_block11_1_bn True\n","conv5_block11_1_relu True\n","conv5_block11_2_conv True\n","conv5_block11_concat True\n","conv5_block12_0_bn True\n","conv5_block12_0_relu True\n","conv5_block12_1_conv True\n","conv5_block12_1_bn True\n","conv5_block12_1_relu True\n","conv5_block12_2_conv True\n","conv5_block12_concat True\n","conv5_block13_0_bn True\n","conv5_block13_0_relu True\n","conv5_block13_1_conv True\n","conv5_block13_1_bn True\n","conv5_block13_1_relu True\n","conv5_block13_2_conv True\n","conv5_block13_concat True\n","conv5_block14_0_bn True\n","conv5_block14_0_relu True\n","conv5_block14_1_conv True\n","conv5_block14_1_bn True\n","conv5_block14_1_relu True\n","conv5_block14_2_conv True\n","conv5_block14_concat True\n","conv5_block15_0_bn True\n","conv5_block15_0_relu True\n","conv5_block15_1_conv True\n","conv5_block15_1_bn True\n","conv5_block15_1_relu True\n","conv5_block15_2_conv True\n","conv5_block15_concat True\n","conv5_block16_0_bn True\n","conv5_block16_0_relu True\n","conv5_block16_1_conv True\n","conv5_block16_1_bn True\n","conv5_block16_1_relu True\n","conv5_block16_2_conv True\n","conv5_block16_concat True\n","bn True\n","relu True\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"CIIbG4Y-Oh0R","executionInfo":{"status":"ok","timestamp":1787464708099,"user_tz":-330,"elapsed":1,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":39,"outputs":[]},{"cell_type":"code","source":["# COMPILE FOR FINE-TUNING\n","\n","model.compile(\n","    optimizer=Adam(learning_rate=1e-5),\n","    loss='sparse_categorical_crossentropy',\n","    metrics=['sparse_categorical_accuracy']\n",")"],"metadata":{"id":"rxJy5ulQOmDi","executionInfo":{"status":"ok","timestamp":1787464708113,"user_tz":-330,"elapsed":11,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":40,"outputs":[]},{"cell_type":"code","source":["# FINE-TUNE DENSENET121\n","\n","fine_tune_epochs = 15\n","\n","fine_tune_callbacks = [\n","\n","    tf.keras.callbacks.EarlyStopping(\n","        monitor='val_loss',\n","        patience=5,\n","        restore_best_weights=True,\n","        verbose=1\n","    ),\n","\n","    tf.keras.callbacks.ReduceLROnPlateau(\n","        monitor='val_loss',\n","        factor=0.2,\n","        patience=2,\n","        min_lr=1e-8,\n","        verbose=1\n","    ),\n","\n","    tf.keras.callbacks.ModelCheckpoint(\n","        'densenet121_finetuned_best.keras',\n","        monitor='val_loss',\n","        save_best_only=True,\n","        verbose=1\n","    )\n","]\n","\n","\n","history_finetune = model.fit(\n","    datagen(\n","        train_paths,\n","        train_labels,\n","        batch_size=batch_size,\n","        epochs=fine_tune_epochs\n","    ),\n","\n","    epochs=fine_tune_epochs,\n","\n","    steps_per_epoch=len(train_paths) // batch_size,\n","\n","    validation_data=datagen(\n","        val_paths,\n","        val_labels,\n","        batch_size=batch_size,\n","        epochs=1\n","    ),\n","\n","    validation_steps=len(val_paths) // batch_size,\n","\n","    callbacks=fine_tune_callbacks\n",")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"GIajgbqcOpLC","executionInfo":{"status":"ok","timestamp":1787464918766,"user_tz":-330,"elapsed":210650,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"1b21ac98-169a-4af2-8ccc-61e741dba963"},"execution_count":41,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/15\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 87ms/step - loss: 0.8715 - sparse_categorical_accuracy: 0.6697\n","Epoch 1: val_loss improved from None to 0.39482, saving model to densenet121_finetuned_best.keras\n","\n","Epoch 1: finished saving model to densenet121_finetuned_best.keras\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m89s\u001b[0m 172ms/step - loss: 0.7858 - sparse_categorical_accuracy: 0.7042 - val_loss: 0.3948 - val_sparse_categorical_accuracy: 0.8514 - learning_rate: 1.0000e-05\n","Epoch 2/15\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 87ms/step - loss: 0.6688 - sparse_categorical_accuracy: 0.7455\n","Epoch 2: val_loss did not improve from 0.39482\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m48s\u001b[0m 88ms/step - loss: 0.6268 - sparse_categorical_accuracy: 0.7660 - val_loss: 0.5655 - val_sparse_categorical_accuracy: 0.8000 - learning_rate: 1.0000e-05\n","Epoch 3/15\n","\u001b[1m  3/202\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m8s\u001b[0m 42ms/step - loss: 0.4532 - sparse_categorical_accuracy: 0.8040"]},{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.13/dist-packages/keras/src/trainers/epoch_iterator.py:164: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches. You may need to use the `.repeat()` function when building your dataset.\n","  self._interrupted_warning()\n"]},{"output_type":"stream","name":"stdout","text":["\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 87ms/step - loss: 0.5380 - sparse_categorical_accuracy: 0.7949\n","Epoch 3: ReduceLROnPlateau reducing learning rate to 1.9999999494757505e-06.\n","\n","Epoch 3: val_loss did not improve from 0.39482\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 88ms/step - loss: 0.5162 - sparse_categorical_accuracy: 0.8058 - val_loss: 0.5468 - val_sparse_categorical_accuracy: 0.8000 - learning_rate: 1.0000e-05\n","Epoch 4/15\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 97ms/step - loss: 0.4781 - sparse_categorical_accuracy: 0.8309\n","Epoch 4: val_loss did not improve from 0.39482\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 98ms/step - loss: 0.4667 - sparse_categorical_accuracy: 0.8336 - val_loss: 0.5401 - val_sparse_categorical_accuracy: 0.8000 - learning_rate: 2.0000e-06\n","Epoch 5/15\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 88ms/step - loss: 0.4679 - sparse_categorical_accuracy: 0.8202\n","Epoch 5: ReduceLROnPlateau reducing learning rate to 3.999999989900971e-07.\n","\n","Epoch 5: val_loss did not improve from 0.39482\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 89ms/step - loss: 0.4622 - sparse_categorical_accuracy: 0.8311 - val_loss: 0.5349 - val_sparse_categorical_accuracy: 0.8000 - learning_rate: 2.0000e-06\n","Epoch 6/15\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 88ms/step - loss: 0.4367 - sparse_categorical_accuracy: 0.8363\n","Epoch 6: val_loss did not improve from 0.39482\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 89ms/step - loss: 0.4343 - sparse_categorical_accuracy: 0.8385 - val_loss: 0.5347 - val_sparse_categorical_accuracy: 0.8000 - learning_rate: 4.0000e-07\n","Epoch 6: early stopping\n","Restoring model weights from the end of the best epoch: 1.\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"NmIPmXqjaXhu","executionInfo":{"status":"ok","timestamp":1787464918774,"user_tz":-330,"elapsed":3,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":41,"outputs":[]},{"cell_type":"markdown","source":["**Test**"],"metadata":{"id":"u1Yxil_2cHKC"}},{"cell_type":"code","source":["def load_test_images(paths):\n","    images = []\n","\n","    for path in paths:\n","        image = load_img(\n","            path,\n","            target_size=(IMAGE_SIZE, IMAGE_SIZE)\n","        )\n","\n","        image = np.array(image) / 255.0\n","        images.append(image)\n","\n","    return np.array(images)"],"metadata":{"id":"cJTtX_o4cGzK","executionInfo":{"status":"ok","timestamp":1787464918778,"user_tz":-330,"elapsed":2,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":42,"outputs":[]},{"cell_type":"code","source":["# Load test images WITHOUT augmentation\n","X_test = load_test_images(test_paths)\n","\n","# Encode test labels\n","y_test = encode_label(test_labels)\n","\n","print(\"Test images:\", X_test.shape)\n","print(\"Test labels:\", y_test.shape)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"uWpwj6hHcJq6","executionInfo":{"status":"ok","timestamp":1787464923893,"user_tz":-330,"elapsed":5113,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"0d9cea86-be02-4056-b16e-6fcaa708360c"},"execution_count":43,"outputs":[{"output_type":"stream","name":"stdout","text":["Test images: (1600, 128, 128, 3)\n","Test labels: (1600,)\n"]}]},{"cell_type":"code","source":["y_pred_prob = model.predict(X_test)\n","\n","y_pred = np.argmax(y_pred_prob, axis=1)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"QQHcTbH0cL0b","executionInfo":{"status":"ok","timestamp":1787464938002,"user_tz":-330,"elapsed":14110,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"599a65d6-2dcf-4bcd-e875-d504427cfd8e"},"execution_count":44,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 36ms/step\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"gXEt14IvcQ-7"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["from sklearn.metrics import confusion_matrix\n","import seaborn as sns\n","import matplotlib.pyplot as plt\n","\n","cm = confusion_matrix(y_test, y_pred)\n","\n","print(cm)\n","\n","plt.figure(figsize=(7, 6))\n","\n","sns.heatmap(\n","    cm,\n","    annot=True,\n","    fmt='d',\n","    cmap='Blues'\n",")\n","\n","plt.xlabel(\"Predicted\")\n","plt.ylabel(\"Actual\")\n","plt.title(\"Confusion Matrix - Fine-Tuned VGG16\")\n","\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":633},"id":"XjoV2kUqcTJr","executionInfo":{"status":"ok","timestamp":1787464938291,"user_tz":-330,"elapsed":264,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"e7d12020-ff07-47ba-fe34-94907ee08a95"},"execution_count":45,"outputs":[{"output_type":"stream","name":"stdout","text":["[[378   1  16   5]\n"," [  2 385  10   3]\n"," [ 61  48 259  32]\n"," [ 32  46  76 246]]\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 700x600 with 2 Axes>"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"code","source":["from sklearn.metrics import classification_report\n","\n","class_names = sorted(os.listdir(train_dir))\n","\n","print(\n","    classification_report(\n","        y_test,\n","        y_pred,\n","        target_names=class_names\n","    )\n",")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"101ZR_CPcZeM","executionInfo":{"status":"ok","timestamp":1787464938358,"user_tz":-330,"elapsed":64,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"c335d29b-f944-4386-b5fa-901a95e5beec"},"execution_count":46,"outputs":[{"output_type":"stream","name":"stdout","text":["              precision    recall  f1-score   support\n","\n","      glioma       0.80      0.94      0.87       400\n","  meningioma       0.80      0.96      0.88       400\n","     notumor       0.72      0.65      0.68       400\n","   pituitary       0.86      0.61      0.72       400\n","\n","    accuracy                           0.79      1600\n","   macro avg       0.79      0.79      0.78      1600\n","weighted avg       0.79      0.79      0.78      1600\n","\n"]}]},{"cell_type":"code","source":["from sklearn.metrics import accuracy_score\n","\n","accuracy = accuracy_score(y_test, y_pred)\n","\n","print(f\"Test Accuracy: {accuracy:.4f}\")\n","print(f\"Test Accuracy: {accuracy * 100:.2f}%\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"T6GbXqQMccuE","executionInfo":{"status":"ok","timestamp":1787464938361,"user_tz":-330,"elapsed":21,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"7d7effb0-f1a4-4de2-99a7-d131e5407465"},"execution_count":47,"outputs":[{"output_type":"stream","name":"stdout","text":["Test Accuracy: 0.7925\n","Test Accuracy: 79.25%\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"WwjdM_9Bcful"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["import numpy as np\n","import tensorflow as tf\n","from tensorflow.keras.models import load_model\n","from sklearn.metrics import accuracy_score\n","\n","# LOAD BOTH MODELS\n","\n","# Original VGG16 model\n","original_model = load_model(\"/content/drive/MyDrive/cancer-cnn/densenet121_stage1_best.keras\")\n","\n","# Fine-tuned VGG16 model\n","finetuned_model = load_model(\"/content/drive/MyDrive/cancer-cnn/densenet121_finetuned_best.keras\")\n","\n","# LOAD TEST DATA\n","X_test = load_test_images(test_paths)\n","y_test = encode_label(test_labels)\n","\n","# PREDICTIONS - ORIGINAL MODEL\n","original_prob = original_model.predict(\n","    X_test,\n","    verbose=1\n",")\n","\n","original_pred = np.argmax(\n","    original_prob,\n","    axis=1\n",")\n","\n","original_accuracy = accuracy_score(\n","    y_test,\n","    original_pred\n",")\n","\n","\n","# PREDICTIONS - FINE-TUNED MODEL\n","finetuned_prob = finetuned_model.predict(\n","    X_test,\n","    verbose=1\n",")\n","finetuned_pred = np.argmax(\n","    finetuned_prob,\n","    axis=1\n",")\n","finetuned_accuracy = accuracy_score(\n","    y_test,\n","    finetuned_pred\n",")\n","\n","\n","# PRINT RESULTS\n","print(\"        MODEL ACCURACY COMPARISON\")\n","print(\" \")\n","\n","print(\n","    f\"Original VGG16      : \"\n","    f\"{original_accuracy * 100:.2f}%\"\n",")\n","\n","print(\n","    f\"Fine-tuned VGG16    : \"\n","    f\"{finetuned_accuracy * 100:.2f}%\"\n",")\n","\n","print(\" \")\n","\n","improvement = (\n","    finetuned_accuracy - original_accuracy\n",") * 100\n","\n","print(\n","    f\"Improvement         : \"\n","    f\"{improvement:+.2f} percentage points\"\n",")\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"FUzxK7bvdLKC","executionInfo":{"status":"ok","timestamp":1787465292145,"user_tz":-330,"elapsed":47920,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"4bac876c-00b8-4e4c-dac1-7cc54f15babe"},"execution_count":48,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m16s\u001b[0m 33ms/step\n","\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 33ms/step\n","        MODEL ACCURACY COMPARISON\n"," \n","Original VGG16      : 4.31%\n","Fine-tuned VGG16    : 5.94%\n"," \n","Improvement         : +1.62 percentage points\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"XOW2SUZ4fMqH","executionInfo":{"status":"ok","timestamp":1787465292169,"user_tz":-330,"elapsed":26,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":48,"outputs":[]},{"cell_type":"markdown","source":["**prediction system**"],"metadata":{"id":"V1CJw3VpneEK"}},{"cell_type":"code","source":["from tensorflow.keras.models import load_model\n","model = load_model('/content/drive/MyDrive/cancer-cnn/densenet121_finetuned_best.keras')"],"metadata":{"id":"QOGO9Cg4fYaR","executionInfo":{"status":"ok","timestamp":1787474426115,"user_tz":-330,"elapsed":16065,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":8,"outputs":[]},{"cell_type":"code","source":["# IMPORTANT:\n","# This mapping matches the output you observed:\n","# model output 0 -> pituitary\n","# model output 1 -> notumor\n","# model output  -> meningioma\n","# model output 3 -> glioma\n","\n","\n","class_names = [\n","    \"pituitary\",\n","    \"notumor\",\n","    \"meningioma\",\n","    \"glioma\"\n","]"],"metadata":{"id":"wo8iwPFOfYXu","executionInfo":{"status":"ok","timestamp":1787465295912,"user_tz":-330,"elapsed":36,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":50,"outputs":[]},{"cell_type":"code","source":["import matplotlib.pyplot as plt\n","from tensorflow.keras.utils import load_img, img_to_array\n","import numpy as np\n","\n","def predict_image(image_path, model):\n","\n","    # Load image\n","    image = load_img(\n","        image_path,\n","        target_size=(IMAGE_SIZE, IMAGE_SIZE)\n","    )\n","\n","    # Convert image to array\n","    image_array = img_to_array(image)\n","\n","    # Normalize\n","    image_array = image_array / 255.0\n","\n","    # Add batch dimension\n","    input_image = np.expand_dims(image_array, axis=0)\n","\n","    # Predict\n","    prediction = model.predict(input_image, verbose=0)[0]\n","\n","    predicted_index = np.argmax(prediction)\n","    predicted_class = class_names[predicted_index]\n","    confidence = prediction[predicted_index] * 100\n","\n","    # Display image\n","    plt.figure(figsize=(6, 6))\n","    plt.imshow(image)\n","    plt.axis(\"off\")\n","\n","    plt.title(\n","        f\"Prediction: {predicted_class}\\n\"\n","        f\"Confidence: {confidence:.2f}%\"\n","    )\n","\n","    plt.show()\n","\n","    # Print probabilities\n","    print(\"MRI PREDICTION\")\n","    print(\" \")\n","\n","    for i, class_name in enumerate(class_names):\n","        print(\n","            f\"{class_name:12s}: \"\n","            f\"{prediction[i] * 100:.2f}%\"\n","        )\n","\n","    print(\" \")\n","    print(f\"Prediction : {predicted_class}\")\n","    print(f\"Confidence : {confidence:.2f}%\")\n","\n","    return predicted_class, confidence"],"metadata":{"id":"rOBg6snommAE","executionInfo":{"status":"ok","timestamp":1787465295917,"user_tz":-330,"elapsed":2,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":51,"outputs":[]},{"cell_type":"code","source":[],"metadata":{"id":"qnPgpAXKmlzu","executionInfo":{"status":"ok","timestamp":1787465295938,"user_tz":-330,"elapsed":20,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":51,"outputs":[]},{"cell_type":"code","source":["predict_image(\n","    \"/content/drive/MyDrive/cancer-cnn/extracted data/Testing/glioma/Te-gl_131.jpg\",\n","    model\n",")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":716},"id":"Jd3h7DCZfMgx","executionInfo":{"status":"ok","timestamp":1787465316726,"user_tz":-330,"elapsed":20786,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"7db8055a-0a7d-4bd5-8e67-74f88b2173dc"},"execution_count":52,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 600x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["MRI PREDICTION\n"," \n","pituitary   : 33.25%\n","notumor     : 13.57%\n","meningioma  : 2.26%\n","glioma      : 50.92%\n"," \n","Prediction : glioma\n","Confidence : 50.92%\n"]},{"output_type":"execute_result","data":{"text/plain":["('glioma', np.float32(50.919937))"]},"metadata":{},"execution_count":52}]},{"cell_type":"code","source":["predict_image(\n","    \"/content/drive/MyDrive/cancer-cnn/extracted data/Testing/meningioma/Te-aug-me_18.jpg\",\n","    model\n",")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":716},"id":"DF6fc_EqfyCU","executionInfo":{"status":"ok","timestamp":1787465316735,"user_tz":-330,"elapsed":6,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"030a239b-1b46-434a-c7ab-777df22d5367"},"execution_count":53,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 600x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["MRI PREDICTION\n"," \n","pituitary   : 2.70%\n","notumor     : 7.39%\n","meningioma  : 12.62%\n","glioma      : 77.29%\n"," \n","Prediction : glioma\n","Confidence : 77.29%\n"]},{"output_type":"execute_result","data":{"text/plain":["('glioma', np.float32(77.29005))"]},"metadata":{},"execution_count":53}]},{"cell_type":"code","source":["predict_image(\n","    \"/content/drive/MyDrive/cancer-cnn/extracted data/Testing/notumor/Te-no_127.jpg\",\n","    model\n",")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":716},"id":"qYX-eDWAieBA","executionInfo":{"status":"ok","timestamp":1787465316952,"user_tz":-330,"elapsed":215,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"035522c1-6b65-418f-ff12-eb134a2ff392"},"execution_count":54,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 600x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["MRI PREDICTION\n"," \n","pituitary   : 0.03%\n","notumor     : 99.94%\n","meningioma  : 0.02%\n","glioma      : 0.01%\n"," \n","Prediction : notumor\n","Confidence : 99.94%\n"]},{"output_type":"execute_result","data":{"text/plain":["('notumor', np.float32(99.93533))"]},"metadata":{},"execution_count":54}]},{"cell_type":"code","source":["predict_image(\n","    \"/content/drive/MyDrive/cancer-cnn/extracted data/Testing/pituitary/Te-pi_167.jpg\",\n","    model\n",")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":716},"id":"lUbqlDdqiegI","executionInfo":{"status":"ok","timestamp":1787465317116,"user_tz":-330,"elapsed":162,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"8dd1f8b9-6895-4f8d-8799-ed6091fb5ef1"},"execution_count":55,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 600x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["MRI PREDICTION\n"," \n","pituitary   : 84.17%\n","notumor     : 7.83%\n","meningioma  : 7.85%\n","glioma      : 0.15%\n"," \n","Prediction : pituitary\n","Confidence : 84.17%\n"]},{"output_type":"execute_result","data":{"text/plain":["('pituitary', np.float32(84.17265))"]},"metadata":{},"execution_count":55}]},{"cell_type":"code","source":[],"metadata":{"id":"fSuYzndkjHRk","executionInfo":{"status":"ok","timestamp":1787465317120,"user_tz":-330,"elapsed":2,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":55,"outputs":[]},{"cell_type":"code","source":["print(os.listdir(train_dir))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"2m8tygzSqLYM","executionInfo":{"status":"ok","timestamp":1787465317137,"user_tz":-330,"elapsed":14,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"1fbf4403-4e7a-420c-ec3f-183f21432c11"},"execution_count":56,"outputs":[{"output_type":"stream","name":"stdout","text":["['glioma', 'pituitary', 'meningioma', 'notumor']\n"]}]},{"cell_type":"markdown","source":["**Training summery**"],"metadata":{"id":"pNiZBwZ7x_sw"}},{"cell_type":"code","source":["model = tf.keras.models.load_model(\n","    \"/content/drive/MyDrive/cancer-cnn/densenet121_stage1_best.keras\"\n",")\n","\n","model.summary()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":481},"id":"SeidBreEyDqv","executionInfo":{"status":"ok","timestamp":1787474538139,"user_tz":-330,"elapsed":7849,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"3353db5a-2c57-496e-9857-05ed552825da"},"execution_count":11,"outputs":[{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential\"\u001b[0m\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ densenet121 (\u001b[38;5;33mFunctional\u001b[0m)        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m1024\u001b[0m)     │     \u001b[38;5;34m7,037,504\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ global_average_pooling2d        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1024\u001b[0m)           │             \u001b[38;5;34m0\u001b[0m │\n","│ (\u001b[38;5;33mGlobalAveragePooling2D\u001b[0m)        │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │       \u001b[38;5;34m262,400\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │         \u001b[38;5;34m1,024\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │        \u001b[38;5;34m32,896\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_1           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │           \u001b[38;5;34m512\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m)              │           \u001b[38;5;34m516\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ densenet121 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Functional</span>)        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1024</span>)     │     <span style=\"color: #00af00; text-decoration-color: #00af00\">7,037,504</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ global_average_pooling2d        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1024</span>)           │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">GlobalAveragePooling2D</span>)        │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │       <span style=\"color: #00af00; text-decoration-color: #00af00\">262,400</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,024</span> │\n","│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">32,896</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_1           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │           <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> │\n","│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">516</span> │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m7,928,014\u001b[0m (30.24 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">7,928,014</span> (30.24 MB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m296,580\u001b[0m (1.13 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">296,580</span> (1.13 MB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m7,038,272\u001b[0m (26.85 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">7,038,272</span> (26.85 MB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Optimizer params: \u001b[0m\u001b[38;5;34m593,162\u001b[0m (2.26 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Optimizer params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">593,162</span> (2.26 MB)\n","</pre>\n"]},"metadata":{}}]},{"cell_type":"code","source":["for i, layer in enumerate(model.layers):\n","    print(i, layer.name, layer.trainable)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"R9v-S4otyDmH","executionInfo":{"status":"ok","timestamp":1787474544615,"user_tz":-330,"elapsed":23,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"ea040faf-3d5d-421b-af4f-5d67418b0e43"},"execution_count":12,"outputs":[{"output_type":"stream","name":"stdout","text":["0 densenet121 True\n","1 global_average_pooling2d True\n","2 dense True\n","3 batch_normalization True\n","4 dropout True\n","5 dense_1 True\n","6 batch_normalization_1 True\n","7 dropout_1 True\n","8 dense_2 True\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"A9krlRhlyDjY"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["model = tf.keras.models.load_model(\n","    \"/content/drive/MyDrive/cancer-cnn/densenet121_finetuned_best.keras\"\n",")\n","\n","model.summary()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":481},"id":"HvRr2nxaxwpW","executionInfo":{"status":"ok","timestamp":1787474448508,"user_tz":-330,"elapsed":4536,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"8358a703-b135-4b75-d368-d2badca2b9d5"},"execution_count":9,"outputs":[{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential\"\u001b[0m\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ densenet121 (\u001b[38;5;33mFunctional\u001b[0m)        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m1024\u001b[0m)     │     \u001b[38;5;34m7,037,504\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ global_average_pooling2d        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1024\u001b[0m)           │             \u001b[38;5;34m0\u001b[0m │\n","│ (\u001b[38;5;33mGlobalAveragePooling2D\u001b[0m)        │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │       \u001b[38;5;34m262,400\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │         \u001b[38;5;34m1,024\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │        \u001b[38;5;34m32,896\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_1           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │           \u001b[38;5;34m512\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m)              │           \u001b[38;5;34m516\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ densenet121 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Functional</span>)        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1024</span>)     │     <span style=\"color: #00af00; text-decoration-color: #00af00\">7,037,504</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ global_average_pooling2d        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1024</span>)           │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">GlobalAveragePooling2D</span>)        │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │       <span style=\"color: #00af00; text-decoration-color: #00af00\">262,400</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,024</span> │\n","│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">32,896</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_1           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │           <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> │\n","│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">516</span> │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m12,248,270\u001b[0m (46.72 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">12,248,270</span> (46.72 MB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m2,456,708\u001b[0m (9.37 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">2,456,708</span> (9.37 MB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m4,878,144\u001b[0m (18.61 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">4,878,144</span> (18.61 MB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Optimizer params: \u001b[0m\u001b[38;5;34m4,913,418\u001b[0m (18.74 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Optimizer params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">4,913,418</span> (18.74 MB)\n","</pre>\n"]},"metadata":{}}]},{"cell_type":"code","source":["for i, layer in enumerate(model.layers):\n","    print(i, layer.name, layer.trainable)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"vwuFGV9nx31l","executionInfo":{"status":"ok","timestamp":1787474454082,"user_tz":-330,"elapsed":9,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"0056bf1f-8314-4a8f-c21b-44235abd59db"},"execution_count":10,"outputs":[{"output_type":"stream","name":"stdout","text":["0 densenet121 True\n","1 global_average_pooling2d True\n","2 dense True\n","3 batch_normalization True\n","4 dropout True\n","5 dense_1 True\n","6 batch_normalization_1 True\n","7 dropout_1 True\n","8 dense_2 True\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"gjP1v6lVx6TT"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["base_model = model.get_layer('densenet121')\n","\n","for i, layer in enumerate(base_model.layers):\n","    print(i, layer.name, layer.__class__.__name__)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"wCC5T402x9Xn","executionInfo":{"status":"ok","timestamp":1787474880521,"user_tz":-330,"elapsed":68,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"f0376923-c7d3-443a-8836-303c29591342"},"execution_count":13,"outputs":[{"output_type":"stream","name":"stdout","text":["0 input_layer InputLayer\n","1 zero_padding2d ZeroPadding2D\n","2 conv1_conv Conv2D\n","3 conv1_bn BatchNormalization\n","4 conv1_relu Activation\n","5 zero_padding2d_1 ZeroPadding2D\n","6 pool1 MaxPooling2D\n","7 conv2_block1_0_bn BatchNormalization\n","8 conv2_block1_0_relu Activation\n","9 conv2_block1_1_conv Conv2D\n","10 conv2_block1_1_bn BatchNormalization\n","11 conv2_block1_1_relu Activation\n","12 conv2_block1_2_conv Conv2D\n","13 conv2_block1_concat Concatenate\n","14 conv2_block2_0_bn BatchNormalization\n","15 conv2_block2_0_relu Activation\n","16 conv2_block2_1_conv Conv2D\n","17 conv2_block2_1_bn BatchNormalization\n","18 conv2_block2_1_relu Activation\n","19 conv2_block2_2_conv Conv2D\n","20 conv2_block2_concat Concatenate\n","21 conv2_block3_0_bn BatchNormalization\n","22 conv2_block3_0_relu Activation\n","23 conv2_block3_1_conv Conv2D\n","24 conv2_block3_1_bn BatchNormalization\n","25 conv2_block3_1_relu Activation\n","26 conv2_block3_2_conv Conv2D\n","27 conv2_block3_concat Concatenate\n","28 conv2_block4_0_bn BatchNormalization\n","29 conv2_block4_0_relu Activation\n","30 conv2_block4_1_conv Conv2D\n","31 conv2_block4_1_bn BatchNormalization\n","32 conv2_block4_1_relu Activation\n","33 conv2_block4_2_conv Conv2D\n","34 conv2_block4_concat Concatenate\n","35 conv2_block5_0_bn BatchNormalization\n","36 conv2_block5_0_relu Activation\n","37 conv2_block5_1_conv Conv2D\n","38 conv2_block5_1_bn BatchNormalization\n","39 conv2_block5_1_relu Activation\n","40 conv2_block5_2_conv Conv2D\n","41 conv2_block5_concat Concatenate\n","42 conv2_block6_0_bn BatchNormalization\n","43 conv2_block6_0_relu Activation\n","44 conv2_block6_1_conv Conv2D\n","45 conv2_block6_1_bn BatchNormalization\n","46 conv2_block6_1_relu Activation\n","47 conv2_block6_2_conv Conv2D\n","48 conv2_block6_concat Concatenate\n","49 pool2_bn BatchNormalization\n","50 pool2_relu Activation\n","51 pool2_conv Conv2D\n","52 pool2_pool AveragePooling2D\n","53 conv3_block1_0_bn BatchNormalization\n","54 conv3_block1_0_relu Activation\n","55 conv3_block1_1_conv Conv2D\n","56 conv3_block1_1_bn BatchNormalization\n","57 conv3_block1_1_relu Activation\n","58 conv3_block1_2_conv Conv2D\n","59 conv3_block1_concat Concatenate\n","60 conv3_block2_0_bn BatchNormalization\n","61 conv3_block2_0_relu Activation\n","62 conv3_block2_1_conv Conv2D\n","63 conv3_block2_1_bn BatchNormalization\n","64 conv3_block2_1_relu Activation\n","65 conv3_block2_2_conv Conv2D\n","66 conv3_block2_concat Concatenate\n","67 conv3_block3_0_bn BatchNormalization\n","68 conv3_block3_0_relu Activation\n","69 conv3_block3_1_conv Conv2D\n","70 conv3_block3_1_bn BatchNormalization\n","71 conv3_block3_1_relu Activation\n","72 conv3_block3_2_conv Conv2D\n","73 conv3_block3_concat Concatenate\n","74 conv3_block4_0_bn BatchNormalization\n","75 conv3_block4_0_relu Activation\n","76 conv3_block4_1_conv Conv2D\n","77 conv3_block4_1_bn BatchNormalization\n","78 conv3_block4_1_relu Activation\n","79 conv3_block4_2_conv Conv2D\n","80 conv3_block4_concat Concatenate\n","81 conv3_block5_0_bn BatchNormalization\n","82 conv3_block5_0_relu Activation\n","83 conv3_block5_1_conv Conv2D\n","84 conv3_block5_1_bn BatchNormalization\n","85 conv3_block5_1_relu Activation\n","86 conv3_block5_2_conv Conv2D\n","87 conv3_block5_concat Concatenate\n","88 conv3_block6_0_bn BatchNormalization\n","89 conv3_block6_0_relu Activation\n","90 conv3_block6_1_conv Conv2D\n","91 conv3_block6_1_bn BatchNormalization\n","92 conv3_block6_1_relu Activation\n","93 conv3_block6_2_conv Conv2D\n","94 conv3_block6_concat Concatenate\n","95 conv3_block7_0_bn BatchNormalization\n","96 conv3_block7_0_relu Activation\n","97 conv3_block7_1_conv Conv2D\n","98 conv3_block7_1_bn BatchNormalization\n","99 conv3_block7_1_relu Activation\n","100 conv3_block7_2_conv Conv2D\n","101 conv3_block7_concat Concatenate\n","102 conv3_block8_0_bn BatchNormalization\n","103 conv3_block8_0_relu Activation\n","104 conv3_block8_1_conv Conv2D\n","105 conv3_block8_1_bn BatchNormalization\n","106 conv3_block8_1_relu Activation\n","107 conv3_block8_2_conv Conv2D\n","108 conv3_block8_concat Concatenate\n","109 conv3_block9_0_bn BatchNormalization\n","110 conv3_block9_0_relu Activation\n","111 conv3_block9_1_conv Conv2D\n","112 conv3_block9_1_bn BatchNormalization\n","113 conv3_block9_1_relu Activation\n","114 conv3_block9_2_conv Conv2D\n","115 conv3_block9_concat Concatenate\n","116 conv3_block10_0_bn BatchNormalization\n","117 conv3_block10_0_relu Activation\n","118 conv3_block10_1_conv Conv2D\n","119 conv3_block10_1_bn BatchNormalization\n","120 conv3_block10_1_relu Activation\n","121 conv3_block10_2_conv Conv2D\n","122 conv3_block10_concat Concatenate\n","123 conv3_block11_0_bn BatchNormalization\n","124 conv3_block11_0_relu Activation\n","125 conv3_block11_1_conv Conv2D\n","126 conv3_block11_1_bn BatchNormalization\n","127 conv3_block11_1_relu Activation\n","128 conv3_block11_2_conv Conv2D\n","129 conv3_block11_concat Concatenate\n","130 conv3_block12_0_bn BatchNormalization\n","131 conv3_block12_0_relu Activation\n","132 conv3_block12_1_conv Conv2D\n","133 conv3_block12_1_bn BatchNormalization\n","134 conv3_block12_1_relu Activation\n","135 conv3_block12_2_conv Conv2D\n","136 conv3_block12_concat Concatenate\n","137 pool3_bn BatchNormalization\n","138 pool3_relu Activation\n","139 pool3_conv Conv2D\n","140 pool3_pool AveragePooling2D\n","141 conv4_block1_0_bn BatchNormalization\n","142 conv4_block1_0_relu Activation\n","143 conv4_block1_1_conv Conv2D\n","144 conv4_block1_1_bn BatchNormalization\n","145 conv4_block1_1_relu Activation\n","146 conv4_block1_2_conv Conv2D\n","147 conv4_block1_concat Concatenate\n","148 conv4_block2_0_bn BatchNormalization\n","149 conv4_block2_0_relu Activation\n","150 conv4_block2_1_conv Conv2D\n","151 conv4_block2_1_bn BatchNormalization\n","152 conv4_block2_1_relu Activation\n","153 conv4_block2_2_conv Conv2D\n","154 conv4_block2_concat Concatenate\n","155 conv4_block3_0_bn BatchNormalization\n","156 conv4_block3_0_relu Activation\n","157 conv4_block3_1_conv Conv2D\n","158 conv4_block3_1_bn BatchNormalization\n","159 conv4_block3_1_relu Activation\n","160 conv4_block3_2_conv Conv2D\n","161 conv4_block3_concat Concatenate\n","162 conv4_block4_0_bn BatchNormalization\n","163 conv4_block4_0_relu Activation\n","164 conv4_block4_1_conv Conv2D\n","165 conv4_block4_1_bn BatchNormalization\n","166 conv4_block4_1_relu Activation\n","167 conv4_block4_2_conv Conv2D\n","168 conv4_block4_concat Concatenate\n","169 conv4_block5_0_bn BatchNormalization\n","170 conv4_block5_0_relu Activation\n","171 conv4_block5_1_conv Conv2D\n","172 conv4_block5_1_bn BatchNormalization\n","173 conv4_block5_1_relu Activation\n","174 conv4_block5_2_conv Conv2D\n","175 conv4_block5_concat Concatenate\n","176 conv4_block6_0_bn BatchNormalization\n","177 conv4_block6_0_relu Activation\n","178 conv4_block6_1_conv Conv2D\n","179 conv4_block6_1_bn BatchNormalization\n","180 conv4_block6_1_relu Activation\n","181 conv4_block6_2_conv Conv2D\n","182 conv4_block6_concat Concatenate\n","183 conv4_block7_0_bn BatchNormalization\n","184 conv4_block7_0_relu Activation\n","185 conv4_block7_1_conv Conv2D\n","186 conv4_block7_1_bn BatchNormalization\n","187 conv4_block7_1_relu Activation\n","188 conv4_block7_2_conv Conv2D\n","189 conv4_block7_concat Concatenate\n","190 conv4_block8_0_bn BatchNormalization\n","191 conv4_block8_0_relu Activation\n","192 conv4_block8_1_conv Conv2D\n","193 conv4_block8_1_bn BatchNormalization\n","194 conv4_block8_1_relu Activation\n","195 conv4_block8_2_conv Conv2D\n","196 conv4_block8_concat Concatenate\n","197 conv4_block9_0_bn BatchNormalization\n","198 conv4_block9_0_relu Activation\n","199 conv4_block9_1_conv Conv2D\n","200 conv4_block9_1_bn BatchNormalization\n","201 conv4_block9_1_relu Activation\n","202 conv4_block9_2_conv Conv2D\n","203 conv4_block9_concat Concatenate\n","204 conv4_block10_0_bn BatchNormalization\n","205 conv4_block10_0_relu Activation\n","206 conv4_block10_1_conv Conv2D\n","207 conv4_block10_1_bn BatchNormalization\n","208 conv4_block10_1_relu Activation\n","209 conv4_block10_2_conv Conv2D\n","210 conv4_block10_concat Concatenate\n","211 conv4_block11_0_bn BatchNormalization\n","212 conv4_block11_0_relu Activation\n","213 conv4_block11_1_conv Conv2D\n","214 conv4_block11_1_bn BatchNormalization\n","215 conv4_block11_1_relu Activation\n","216 conv4_block11_2_conv Conv2D\n","217 conv4_block11_concat Concatenate\n","218 conv4_block12_0_bn BatchNormalization\n","219 conv4_block12_0_relu Activation\n","220 conv4_block12_1_conv Conv2D\n","221 conv4_block12_1_bn BatchNormalization\n","222 conv4_block12_1_relu Activation\n","223 conv4_block12_2_conv Conv2D\n","224 conv4_block12_concat Concatenate\n","225 conv4_block13_0_bn BatchNormalization\n","226 conv4_block13_0_relu Activation\n","227 conv4_block13_1_conv Conv2D\n","228 conv4_block13_1_bn BatchNormalization\n","229 conv4_block13_1_relu Activation\n","230 conv4_block13_2_conv Conv2D\n","231 conv4_block13_concat Concatenate\n","232 conv4_block14_0_bn BatchNormalization\n","233 conv4_block14_0_relu Activation\n","234 conv4_block14_1_conv Conv2D\n","235 conv4_block14_1_bn BatchNormalization\n","236 conv4_block14_1_relu Activation\n","237 conv4_block14_2_conv Conv2D\n","238 conv4_block14_concat Concatenate\n","239 conv4_block15_0_bn BatchNormalization\n","240 conv4_block15_0_relu Activation\n","241 conv4_block15_1_conv Conv2D\n","242 conv4_block15_1_bn BatchNormalization\n","243 conv4_block15_1_relu Activation\n","244 conv4_block15_2_conv Conv2D\n","245 conv4_block15_concat Concatenate\n","246 conv4_block16_0_bn BatchNormalization\n","247 conv4_block16_0_relu Activation\n","248 conv4_block16_1_conv Conv2D\n","249 conv4_block16_1_bn BatchNormalization\n","250 conv4_block16_1_relu Activation\n","251 conv4_block16_2_conv Conv2D\n","252 conv4_block16_concat Concatenate\n","253 conv4_block17_0_bn BatchNormalization\n","254 conv4_block17_0_relu Activation\n","255 conv4_block17_1_conv Conv2D\n","256 conv4_block17_1_bn BatchNormalization\n","257 conv4_block17_1_relu Activation\n","258 conv4_block17_2_conv Conv2D\n","259 conv4_block17_concat Concatenate\n","260 conv4_block18_0_bn BatchNormalization\n","261 conv4_block18_0_relu Activation\n","262 conv4_block18_1_conv Conv2D\n","263 conv4_block18_1_bn BatchNormalization\n","264 conv4_block18_1_relu Activation\n","265 conv4_block18_2_conv Conv2D\n","266 conv4_block18_concat Concatenate\n","267 conv4_block19_0_bn BatchNormalization\n","268 conv4_block19_0_relu Activation\n","269 conv4_block19_1_conv Conv2D\n","270 conv4_block19_1_bn BatchNormalization\n","271 conv4_block19_1_relu Activation\n","272 conv4_block19_2_conv Conv2D\n","273 conv4_block19_concat Concatenate\n","274 conv4_block20_0_bn BatchNormalization\n","275 conv4_block20_0_relu Activation\n","276 conv4_block20_1_conv Conv2D\n","277 conv4_block20_1_bn BatchNormalization\n","278 conv4_block20_1_relu Activation\n","279 conv4_block20_2_conv Conv2D\n","280 conv4_block20_concat Concatenate\n","281 conv4_block21_0_bn BatchNormalization\n","282 conv4_block21_0_relu Activation\n","283 conv4_block21_1_conv Conv2D\n","284 conv4_block21_1_bn BatchNormalization\n","285 conv4_block21_1_relu Activation\n","286 conv4_block21_2_conv Conv2D\n","287 conv4_block21_concat Concatenate\n","288 conv4_block22_0_bn BatchNormalization\n","289 conv4_block22_0_relu Activation\n","290 conv4_block22_1_conv Conv2D\n","291 conv4_block22_1_bn BatchNormalization\n","292 conv4_block22_1_relu Activation\n","293 conv4_block22_2_conv Conv2D\n","294 conv4_block22_concat Concatenate\n","295 conv4_block23_0_bn BatchNormalization\n","296 conv4_block23_0_relu Activation\n","297 conv4_block23_1_conv Conv2D\n","298 conv4_block23_1_bn BatchNormalization\n","299 conv4_block23_1_relu Activation\n","300 conv4_block23_2_conv Conv2D\n","301 conv4_block23_concat Concatenate\n","302 conv4_block24_0_bn BatchNormalization\n","303 conv4_block24_0_relu Activation\n","304 conv4_block24_1_conv Conv2D\n","305 conv4_block24_1_bn BatchNormalization\n","306 conv4_block24_1_relu Activation\n","307 conv4_block24_2_conv Conv2D\n","308 conv4_block24_concat Concatenate\n","309 pool4_bn BatchNormalization\n","310 pool4_relu Activation\n","311 pool4_conv Conv2D\n","312 pool4_pool AveragePooling2D\n","313 conv5_block1_0_bn BatchNormalization\n","314 conv5_block1_0_relu Activation\n","315 conv5_block1_1_conv Conv2D\n","316 conv5_block1_1_bn BatchNormalization\n","317 conv5_block1_1_relu Activation\n","318 conv5_block1_2_conv Conv2D\n","319 conv5_block1_concat Concatenate\n","320 conv5_block2_0_bn BatchNormalization\n","321 conv5_block2_0_relu Activation\n","322 conv5_block2_1_conv Conv2D\n","323 conv5_block2_1_bn BatchNormalization\n","324 conv5_block2_1_relu Activation\n","325 conv5_block2_2_conv Conv2D\n","326 conv5_block2_concat Concatenate\n","327 conv5_block3_0_bn BatchNormalization\n","328 conv5_block3_0_relu Activation\n","329 conv5_block3_1_conv Conv2D\n","330 conv5_block3_1_bn BatchNormalization\n","331 conv5_block3_1_relu Activation\n","332 conv5_block3_2_conv Conv2D\n","333 conv5_block3_concat Concatenate\n","334 conv5_block4_0_bn BatchNormalization\n","335 conv5_block4_0_relu Activation\n","336 conv5_block4_1_conv Conv2D\n","337 conv5_block4_1_bn BatchNormalization\n","338 conv5_block4_1_relu Activation\n","339 conv5_block4_2_conv Conv2D\n","340 conv5_block4_concat Concatenate\n","341 conv5_block5_0_bn BatchNormalization\n","342 conv5_block5_0_relu Activation\n","343 conv5_block5_1_conv Conv2D\n","344 conv5_block5_1_bn BatchNormalization\n","345 conv5_block5_1_relu Activation\n","346 conv5_block5_2_conv Conv2D\n","347 conv5_block5_concat Concatenate\n","348 conv5_block6_0_bn BatchNormalization\n","349 conv5_block6_0_relu Activation\n","350 conv5_block6_1_conv Conv2D\n","351 conv5_block6_1_bn BatchNormalization\n","352 conv5_block6_1_relu Activation\n","353 conv5_block6_2_conv Conv2D\n","354 conv5_block6_concat Concatenate\n","355 conv5_block7_0_bn BatchNormalization\n","356 conv5_block7_0_relu Activation\n","357 conv5_block7_1_conv Conv2D\n","358 conv5_block7_1_bn BatchNormalization\n","359 conv5_block7_1_relu Activation\n","360 conv5_block7_2_conv Conv2D\n","361 conv5_block7_concat Concatenate\n","362 conv5_block8_0_bn BatchNormalization\n","363 conv5_block8_0_relu Activation\n","364 conv5_block8_1_conv Conv2D\n","365 conv5_block8_1_bn BatchNormalization\n","366 conv5_block8_1_relu Activation\n","367 conv5_block8_2_conv Conv2D\n","368 conv5_block8_concat Concatenate\n","369 conv5_block9_0_bn BatchNormalization\n","370 conv5_block9_0_relu Activation\n","371 conv5_block9_1_conv Conv2D\n","372 conv5_block9_1_bn BatchNormalization\n","373 conv5_block9_1_relu Activation\n","374 conv5_block9_2_conv Conv2D\n","375 conv5_block9_concat Concatenate\n","376 conv5_block10_0_bn BatchNormalization\n","377 conv5_block10_0_relu Activation\n","378 conv5_block10_1_conv Conv2D\n","379 conv5_block10_1_bn BatchNormalization\n","380 conv5_block10_1_relu Activation\n","381 conv5_block10_2_conv Conv2D\n","382 conv5_block10_concat Concatenate\n","383 conv5_block11_0_bn BatchNormalization\n","384 conv5_block11_0_relu Activation\n","385 conv5_block11_1_conv Conv2D\n","386 conv5_block11_1_bn BatchNormalization\n","387 conv5_block11_1_relu Activation\n","388 conv5_block11_2_conv Conv2D\n","389 conv5_block11_concat Concatenate\n","390 conv5_block12_0_bn BatchNormalization\n","391 conv5_block12_0_relu Activation\n","392 conv5_block12_1_conv Conv2D\n","393 conv5_block12_1_bn BatchNormalization\n","394 conv5_block12_1_relu Activation\n","395 conv5_block12_2_conv Conv2D\n","396 conv5_block12_concat Concatenate\n","397 conv5_block13_0_bn BatchNormalization\n","398 conv5_block13_0_relu Activation\n","399 conv5_block13_1_conv Conv2D\n","400 conv5_block13_1_bn BatchNormalization\n","401 conv5_block13_1_relu Activation\n","402 conv5_block13_2_conv Conv2D\n","403 conv5_block13_concat Concatenate\n","404 conv5_block14_0_bn BatchNormalization\n","405 conv5_block14_0_relu Activation\n","406 conv5_block14_1_conv Conv2D\n","407 conv5_block14_1_bn BatchNormalization\n","408 conv5_block14_1_relu Activation\n","409 conv5_block14_2_conv Conv2D\n","410 conv5_block14_concat Concatenate\n","411 conv5_block15_0_bn BatchNormalization\n","412 conv5_block15_0_relu Activation\n","413 conv5_block15_1_conv Conv2D\n","414 conv5_block15_1_bn BatchNormalization\n","415 conv5_block15_1_relu Activation\n","416 conv5_block15_2_conv Conv2D\n","417 conv5_block15_concat Concatenate\n","418 conv5_block16_0_bn BatchNormalization\n","419 conv5_block16_0_relu Activation\n","420 conv5_block16_1_conv Conv2D\n","421 conv5_block16_1_bn BatchNormalization\n","422 conv5_block16_1_relu Activation\n","423 conv5_block16_2_conv Conv2D\n","424 conv5_block16_concat Concatenate\n","425 bn BatchNormalization\n","426 relu Activation\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"EniVT6v7x9SG"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["# **Finetuning the stage 1 model with different sets of parameters**"],"metadata":{"id":"kBDbwqWd0Ftn"}},{"cell_type":"code","source":["model = tf.keras.models.load_model(\"/content/drive/MyDrive/cancer-cnn/densenet121_stage1_best.keras\")"],"metadata":{"id":"kSx-yQHa0R3n","executionInfo":{"status":"ok","timestamp":1787475288941,"user_tz":-330,"elapsed":3197,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":19,"outputs":[]},{"cell_type":"code","source":["# STAGE 2 - OPTIMIZED FINE TUNING DENSENET121\n","\n","# Load the BEST Stage-1 model\n","model = tf.keras.models.load_model(\n","    '/content/drive/MyDrive/cancer-cnn/densenet121_stage1_best.keras'\n",")\n","\n","# Get DenseNet121 backbone\n","base_model = model.get_layer('densenet121')\n","\n","\n","# FREEZE EVERYTHING FIRST\n","for layer in base_model.layers:\n","    layer.trainable = False\n","\n","\n","# UNFREEZE FROM conv5_block9\n","set_trainable = False\n","\n","for layer in base_model.layers:\n","\n","    if layer.name == 'conv5_block9_0_bn':\n","        set_trainable = True\n","\n","    if set_trainable:\n","\n","        # Keep Batch Normalization layers frozen\n","        if isinstance(layer, tf.keras.layers.BatchNormalization):\n","            layer.trainable = False\n","        else:\n","            layer.trainable = True\n","\n","\n","# KEEP CLASSIFICATION HEAD TRAINABLE\n","for layer in model.layers:\n","\n","    if layer.name != 'densenet121':\n","        layer.trainable = True\n","\n","\n","# CHECK TRAINABLE LAYERS\n","print(\"\\nTrainable DenseNet121 layers:\")\n","\n","for layer in base_model.layers:\n","    if layer.trainable:\n","        print(layer.name, layer.__class__.__name__)\n","\n","\n","# PARAMETER COUNT\n","trainable_params = sum(\n","    tf.keras.backend.count_params(w)\n","    for w in model.trainable_weights\n",")\n","\n","non_trainable_params = sum(\n","    tf.keras.backend.count_params(w)\n","    for w in model.non_trainable_weights\n",")\n","\n","print(\"\\nTrainable parameters:\", trainable_params)\n","print(\"Non-trainable parameters:\", non_trainable_params)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Hqmd2aYK0RTF","executionInfo":{"status":"ok","timestamp":1787475411823,"user_tz":-330,"elapsed":4124,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"ea240477-25bf-4241-d107-e18d44014698"},"execution_count":21,"outputs":[{"output_type":"stream","name":"stdout","text":["\n","Trainable DenseNet121 layers:\n","conv5_block9_0_relu Activation\n","conv5_block9_1_conv Conv2D\n","conv5_block9_1_relu Activation\n","conv5_block9_2_conv Conv2D\n","conv5_block9_concat Concatenate\n","conv5_block10_0_relu Activation\n","conv5_block10_1_conv Conv2D\n","conv5_block10_1_relu Activation\n","conv5_block10_2_conv Conv2D\n","conv5_block10_concat Concatenate\n","conv5_block11_0_relu Activation\n","conv5_block11_1_conv Conv2D\n","conv5_block11_1_relu Activation\n","conv5_block11_2_conv Conv2D\n","conv5_block11_concat Concatenate\n","conv5_block12_0_relu Activation\n","conv5_block12_1_conv Conv2D\n","conv5_block12_1_relu Activation\n","conv5_block12_2_conv Conv2D\n","conv5_block12_concat Concatenate\n","conv5_block13_0_relu Activation\n","conv5_block13_1_conv Conv2D\n","conv5_block13_1_relu Activation\n","conv5_block13_2_conv Conv2D\n","conv5_block13_concat Concatenate\n","conv5_block14_0_relu Activation\n","conv5_block14_1_conv Conv2D\n","conv5_block14_1_relu Activation\n","conv5_block14_2_conv Conv2D\n","conv5_block14_concat Concatenate\n","conv5_block15_0_relu Activation\n","conv5_block15_1_conv Conv2D\n","conv5_block15_1_relu Activation\n","conv5_block15_2_conv Conv2D\n","conv5_block15_concat Concatenate\n","conv5_block16_0_relu Activation\n","conv5_block16_1_conv Conv2D\n","conv5_block16_1_relu Activation\n","conv5_block16_2_conv Conv2D\n","conv5_block16_concat Concatenate\n","relu Activation\n","\n","Trainable parameters: 1492612\n","Non-trainable parameters: 5842240\n"]}]},{"cell_type":"code","source":["# COMPILE FOR OPTIMIZED DENSENET121 FINE-TUNING\n","\n","model.compile(\n","    optimizer=tf.keras.optimizers.AdamW(\n","        learning_rate=3e-6,\n","        weight_decay=1e-4\n","    ),\n","\n","    loss='sparse_categorical_crossentropy',\n","\n","    metrics=['sparse_categorical_accuracy']\n",")"],"metadata":{"id":"XJvkjZZO03q0","executionInfo":{"status":"ok","timestamp":1787475495533,"user_tz":-330,"elapsed":24,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":22,"outputs":[]},{"cell_type":"code","source":["model.summary()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":465},"id":"9u9AQIjr14jl","executionInfo":{"status":"ok","timestamp":1787475503930,"user_tz":-330,"elapsed":63,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"a8789075-8b1d-44fb-cdea-8eec32e3cc24"},"execution_count":23,"outputs":[{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential\"\u001b[0m\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ densenet121 (\u001b[38;5;33mFunctional\u001b[0m)        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m1024\u001b[0m)     │     \u001b[38;5;34m7,037,504\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ global_average_pooling2d        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1024\u001b[0m)           │             \u001b[38;5;34m0\u001b[0m │\n","│ (\u001b[38;5;33mGlobalAveragePooling2D\u001b[0m)        │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │       \u001b[38;5;34m262,400\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │         \u001b[38;5;34m1,024\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │        \u001b[38;5;34m32,896\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_1           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │           \u001b[38;5;34m512\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m)              │           \u001b[38;5;34m516\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ densenet121 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Functional</span>)        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1024</span>)     │     <span style=\"color: #00af00; text-decoration-color: #00af00\">7,037,504</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ global_average_pooling2d        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1024</span>)           │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">GlobalAveragePooling2D</span>)        │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │       <span style=\"color: #00af00; text-decoration-color: #00af00\">262,400</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,024</span> │\n","│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">32,896</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_1           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │           <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> │\n","│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">516</span> │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m7,334,852\u001b[0m (27.98 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">7,334,852</span> (27.98 MB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m1,492,612\u001b[0m (5.69 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">1,492,612</span> (5.69 MB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m5,842,240\u001b[0m (22.29 MB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">5,842,240</span> (22.29 MB)\n","</pre>\n"]},"metadata":{}}]},{"cell_type":"code","source":["# OPTIMIZED DENSENET121 FINE-TUNING\n","\n","IMAGE_SIZE = 128\n","batch_size = 20\n","fine_tune_epochs = 20\n","\n","\n","fine_tune_callbacks = [\n","\n","    tf.keras.callbacks.EarlyStopping(\n","        monitor='val_loss',\n","        patience=5,\n","        restore_best_weights=True,\n","        verbose=1\n","    ),\n","\n","    tf.keras.callbacks.ReduceLROnPlateau(\n","        monitor='val_loss',\n","        factor=0.2,\n","        patience=2,\n","        min_lr=1e-8,\n","        verbose=1\n","    ),\n","\n","    tf.keras.callbacks.ModelCheckpoint(\n","        '/content/drive/MyDrive/cancer-cnn/densenet121_optimized_finetuned_best.keras',\n","        monitor='val_loss',\n","        save_best_only=True,\n","        verbose=1\n","    )\n","]\n","\n","\n","history_densenet121_finetune = model.fit(\n","\n","    datagen(\n","        train_paths,\n","        train_labels,\n","        batch_size=batch_size,\n","        epochs=fine_tune_epochs\n","    ),\n","\n","    epochs=fine_tune_epochs,\n","\n","    steps_per_epoch=len(train_paths) // batch_size,\n","\n","    validation_data=datagen(\n","        val_paths,\n","        val_labels,\n","        batch_size=batch_size,\n","        epochs=1\n","    ),\n","\n","    validation_steps=len(val_paths) // batch_size,\n","\n","    callbacks=fine_tune_callbacks\n",")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"LjB36yuV16mV","executionInfo":{"status":"ok","timestamp":1787477899724,"user_tz":-330,"elapsed":2215740,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"783eb229-737f-406d-9116-b53642c598df"},"execution_count":31,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9s/step - loss: 0.4878 - sparse_categorical_accuracy: 0.8277\n","Epoch 1: val_loss improved from None to 0.30172, saving model to /content/drive/MyDrive/cancer-cnn/densenet121_optimized_finetuned_best.keras\n","\n","Epoch 1: finished saving model to /content/drive/MyDrive/cancer-cnn/densenet121_optimized_finetuned_best.keras\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2039s\u001b[0m 10s/step - loss: 0.4565 - sparse_categorical_accuracy: 0.8342 - val_loss: 0.3017 - val_sparse_categorical_accuracy: 0.9014 - learning_rate: 3.0000e-06\n","Epoch 2/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 83ms/step - loss: 0.4790 - sparse_categorical_accuracy: 0.8239"]},{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.13/dist-packages/keras/src/trainers/epoch_iterator.py:164: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches. You may need to use the `.repeat()` function when building your dataset.\n","  self._interrupted_warning()\n"]},{"output_type":"stream","name":"stdout","text":["\n","Epoch 2: val_loss improved from 0.30172 to 0.20384, saving model to /content/drive/MyDrive/cancer-cnn/densenet121_optimized_finetuned_best.keras\n","\n","Epoch 2: finished saving model to /content/drive/MyDrive/cancer-cnn/densenet121_optimized_finetuned_best.keras\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 93ms/step - loss: 0.4507 - sparse_categorical_accuracy: 0.8323 - val_loss: 0.2038 - val_sparse_categorical_accuracy: 0.9750 - learning_rate: 3.0000e-06\n","Epoch 3/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 91ms/step - loss: 0.4632 - sparse_categorical_accuracy: 0.8320\n","Epoch 3: val_loss improved from 0.20384 to 0.19831, saving model to /content/drive/MyDrive/cancer-cnn/densenet121_optimized_finetuned_best.keras\n","\n","Epoch 3: finished saving model to /content/drive/MyDrive/cancer-cnn/densenet121_optimized_finetuned_best.keras\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 101ms/step - loss: 0.4395 - sparse_categorical_accuracy: 0.8418 - val_loss: 0.1983 - val_sparse_categorical_accuracy: 0.9750 - learning_rate: 3.0000e-06\n","Epoch 4/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 90ms/step - loss: 0.4319 - sparse_categorical_accuracy: 0.8472\n","Epoch 4: val_loss did not improve from 0.19831\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 90ms/step - loss: 0.4277 - sparse_categorical_accuracy: 0.8408 - val_loss: 0.2005 - val_sparse_categorical_accuracy: 0.9750 - learning_rate: 3.0000e-06\n","Epoch 5/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 89ms/step - loss: 0.4226 - sparse_categorical_accuracy: 0.8396\n","Epoch 5: ReduceLROnPlateau reducing learning rate to 6.000000212225132e-07.\n","\n","Epoch 5: val_loss did not improve from 0.19831\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 91ms/step - loss: 0.4241 - sparse_categorical_accuracy: 0.8378 - val_loss: 0.2018 - val_sparse_categorical_accuracy: 0.9750 - learning_rate: 3.0000e-06\n","Epoch 6/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 99ms/step - loss: 0.4322 - sparse_categorical_accuracy: 0.8391\n","Epoch 6: val_loss did not improve from 0.19831\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 100ms/step - loss: 0.4340 - sparse_categorical_accuracy: 0.8381 - val_loss: 0.2040 - val_sparse_categorical_accuracy: 0.9750 - learning_rate: 6.0000e-07\n","Epoch 7/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 93ms/step - loss: 0.4140 - sparse_categorical_accuracy: 0.8463\n","Epoch 7: ReduceLROnPlateau reducing learning rate to 1.2000000424450263e-07.\n","\n","Epoch 7: val_loss did not improve from 0.19831\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 93ms/step - loss: 0.4203 - sparse_categorical_accuracy: 0.8430 - val_loss: 0.2048 - val_sparse_categorical_accuracy: 0.9750 - learning_rate: 6.0000e-07\n","Epoch 8/20\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 93ms/step - loss: 0.4372 - sparse_categorical_accuracy: 0.8374\n","Epoch 8: val_loss did not improve from 0.19831\n","\u001b[1m202/202\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 94ms/step - loss: 0.4256 - sparse_categorical_accuracy: 0.8435 - val_loss: 0.2030 - val_sparse_categorical_accuracy: 0.9750 - learning_rate: 1.2000e-07\n","Epoch 8: early stopping\n","Restoring model weights from the end of the best epoch: 3.\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"ONpHvd5_2AjB"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["def load_test_images(paths):\n","    images = []\n","\n","    for path in paths:\n","        image = load_img(\n","            path,\n","            target_size=(IMAGE_SIZE, IMAGE_SIZE)\n","        )\n","\n","        image = np.array(image) / 255.0\n","        images.append(image)\n","\n","    return np.array(images)"],"metadata":{"id":"LAEIH0A6BgCV","executionInfo":{"status":"ok","timestamp":1787478546680,"user_tz":-330,"elapsed":3,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":32,"outputs":[]},{"cell_type":"code","source":["# Load test images WITHOUT augmentation\n","X_test = load_test_images(test_paths)\n","\n","# Encode test labels\n","y_test = encode_label(test_labels)\n","\n","print(\"Test images:\", X_test.shape)\n","print(\"Test labels:\", y_test.shape)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"SRgmOjjNBheQ","executionInfo":{"status":"ok","timestamp":1787479247400,"user_tz":-330,"elapsed":688990,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"43430839-9a65-4417-9fdb-98d5e148e5c2"},"execution_count":33,"outputs":[{"output_type":"stream","name":"stdout","text":["Test images: (1600, 128, 128, 3)\n","Test labels: (1600,)\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"JE7LYG7xB7uQ"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["model = tf.keras.models.load_model(\"/content/drive/MyDrive/cancer-cnn/densenet121_optimized_finetuned_best.keras\")"],"metadata":{"id":"1zYU2HkbB8rh"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":[],"metadata":{"id":"h3DEMuFVB7kI"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["y_pred_prob = model.predict(X_test)\n","\n","y_pred = np.argmax(y_pred_prob, axis=1)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"ORiOa6nHBkVi","executionInfo":{"status":"ok","timestamp":1787479265624,"user_tz":-330,"elapsed":18221,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"30c1ca21-7d63-4099-9ac2-14532dbb60b0"},"execution_count":34,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m17s\u001b[0m 37ms/step\n"]}]},{"cell_type":"code","source":["from sklearn.metrics import confusion_matrix\n","import seaborn as sns\n","import matplotlib.pyplot as plt\n","\n","cm = confusion_matrix(y_test, y_pred)\n","\n","print(cm)\n","\n","plt.figure(figsize=(7, 6))\n","\n","sns.heatmap(\n","    cm,\n","    annot=True,\n","    fmt='d',\n","    cmap='Blues'\n",")\n","\n","plt.xlabel(\"Predicted\")\n","plt.ylabel(\"Actual\")\n","plt.title(\"Confusion Matrix - Fine-Tuned VGG16\")\n","\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":633},"id":"roUv7V4dBlyK","executionInfo":{"status":"ok","timestamp":1787479266018,"user_tz":-330,"elapsed":391,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"2f242512-a4cf-4fcd-9e31-8eb5a812075c"},"execution_count":35,"outputs":[{"output_type":"stream","name":"stdout","text":["[[385   0  10   5]\n"," [  1 390   7   2]\n"," [ 46  37 289  28]\n"," [ 21  44  71 264]]\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 700x600 with 2 Axes>"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"code","source":["from sklearn.metrics import classification_report\n","\n","class_names = sorted(os.listdir(train_dir))\n","\n","print(\n","    classification_report(\n","        y_test,\n","        y_pred,\n","        target_names=class_names\n","    )\n",")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"ZDOvFV9VBnHN","executionInfo":{"status":"ok","timestamp":1787479266030,"user_tz":-330,"elapsed":11,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"e5640389-606b-4c12-ed77-421776c57e03"},"execution_count":36,"outputs":[{"output_type":"stream","name":"stdout","text":["              precision    recall  f1-score   support\n","\n","      glioma       0.85      0.96      0.90       400\n","  meningioma       0.83      0.97      0.90       400\n","     notumor       0.77      0.72      0.74       400\n","   pituitary       0.88      0.66      0.76       400\n","\n","    accuracy                           0.83      1600\n","   macro avg       0.83      0.83      0.82      1600\n","weighted avg       0.83      0.83      0.82      1600\n","\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"udJyMWisBoRT"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["**pred**"],"metadata":{"id":"3SYoz_ueChoV"}},{"cell_type":"code","source":["  # IMPORTANT:\n","# This mapping matches the output you observed:\n","# model output 0 -> pituitary\n","# model output 1 -> notumor\n","# model output  -> meningioma\n","# model output 3 -> glioma\n","\n","\n","class_names = [\n","    \"pituitary\",\n","    \"notumor\",\n","    \"meningioma\",\n","    \"glioma\"\n","]"],"metadata":{"id":"FVj9sNfJCeb0","executionInfo":{"status":"ok","timestamp":1787479295711,"user_tz":-330,"elapsed":43,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":37,"outputs":[]},{"cell_type":"code","source":["import matplotlib.pyplot as plt\n","from tensorflow.keras.utils import load_img, img_to_array\n","import numpy as np\n","\n","def predict_image(image_path, model):\n","\n","    # Load image\n","    image = load_img(\n","        image_path,\n","        target_size=(IMAGE_SIZE, IMAGE_SIZE)\n","    )\n","\n","    # Convert image to array\n","    image_array = img_to_array(image)\n","\n","    # Normalize\n","    image_array = image_array / 255.0\n","\n","    # Add batch dimension\n","    input_image = np.expand_dims(image_array, axis=0)\n","\n","    # Predict\n","    prediction = model.predict(input_image, verbose=0)[0]\n","\n","    predicted_index = np.argmax(prediction)\n","    predicted_class = class_names[predicted_index]\n","    confidence = prediction[predicted_index] * 100\n","\n","    # Display image\n","    plt.figure(figsize=(6, 6))\n","    plt.imshow(image)\n","    plt.axis(\"off\")\n","\n","    plt.title(\n","        f\"Prediction: {predicted_class}\\n\"\n","        f\"Confidence: {confidence:.2f}%\"\n","    )\n","\n","    plt.show()\n","\n","    # Print probabilities\n","    print(\"MRI PREDICTION\")\n","    print(\" \")\n","\n","    for i, class_name in enumerate(class_names):\n","        print(\n","            f\"{class_name:12s}: \"\n","            f\"{prediction[i] * 100:.2f}%\"\n","        )\n","\n","    print(\" \")\n","    print(f\"Prediction : {predicted_class}\")\n","    print(f\"Confidence : {confidence:.2f}%\")\n","\n","    return predicted_class, confidence"],"metadata":{"id":"uI5YTny5CcbL","executionInfo":{"status":"ok","timestamp":1787479296126,"user_tz":-330,"elapsed":12,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}}},"execution_count":38,"outputs":[]},{"cell_type":"code","source":["predict_image(\n","    \"/content/drive/MyDrive/cancer-cnn/extracted data/Testing/glioma/Te-gl_131.jpg\",\n","    model\n",")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":716},"id":"8umZVl_HCbNj","executionInfo":{"status":"ok","timestamp":1787479317886,"user_tz":-330,"elapsed":17151,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"2b33173b-5840-4ec3-a071-b7ac107f585f"},"execution_count":39,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 600x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["MRI PREDICTION\n"," \n","pituitary   : 27.34%\n","notumor     : 1.28%\n","meningioma  : 1.21%\n","glioma      : 70.17%\n"," \n","Prediction : glioma\n","Confidence : 70.17%\n"]},{"output_type":"execute_result","data":{"text/plain":["('glioma', np.float32(70.168465))"]},"metadata":{},"execution_count":39}]},{"cell_type":"code","source":["predict_image(\n","    \"/content/drive/MyDrive/cancer-cnn/extracted data/Testing/meningioma/Te-aug-me_63.jpg\",\n","    model\n",")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":716},"id":"R-g1W2K0CaOT","executionInfo":{"status":"ok","timestamp":1787479377020,"user_tz":-330,"elapsed":518,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"c4554a24-3845-4b90-f418-467bcdb0c522"},"execution_count":43,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 600x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["MRI PREDICTION\n"," \n","pituitary   : 0.37%\n","notumor     : 4.01%\n","meningioma  : 92.44%\n","glioma      : 3.18%\n"," \n","Prediction : meningioma\n","Confidence : 92.44%\n"]},{"output_type":"execute_result","data":{"text/plain":["('meningioma', np.float32(92.43708))"]},"metadata":{},"execution_count":43}]},{"cell_type":"code","source":["predict_image(\n","    \"/content/drive/MyDrive/cancer-cnn/extracted data/Testing/notumor/Te-no_127.jpg\",\n","    model\n",")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":716},"id":"rLGZGCXcCYSv","executionInfo":{"status":"ok","timestamp":1787479318372,"user_tz":-330,"elapsed":286,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"ea998fe3-f07b-4cda-f1ab-dc78b9216689"},"execution_count":41,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 600x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["MRI PREDICTION\n"," \n","pituitary   : 0.02%\n","notumor     : 99.97%\n","meningioma  : 0.01%\n","glioma      : 0.00%\n"," \n","Prediction : notumor\n","Confidence : 99.97%\n"]},{"output_type":"execute_result","data":{"text/plain":["('notumor', np.float32(99.96924))"]},"metadata":{},"execution_count":41}]},{"cell_type":"code","source":["predict_image(\n","    \"/content/drive/MyDrive/cancer-cnn/extracted data/Testing/pituitary/Te-pi_167.jpg\",\n","    model\n",")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":716},"id":"6MS8EQneCYPG","executionInfo":{"status":"ok","timestamp":1787479318614,"user_tz":-330,"elapsed":240,"user":{"displayName":"K J ASSOCIATES","userId":"10730000755973269396"}},"outputId":"de695d1e-ec94-4b50-8e4b-095b28f45b2d"},"execution_count":42,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 600x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["MRI PREDICTION\n"," \n","pituitary   : 99.64%\n","notumor     : 0.09%\n","meningioma  : 0.18%\n","glioma      : 0.08%\n"," \n","Prediction : pituitary\n","Confidence : 99.64%\n"]},{"output_type":"execute_result","data":{"text/plain":["('pituitary', np.float32(99.64043))"]},"metadata":{},"execution_count":42}]},{"cell_type":"code","source":[],"metadata":{"id":"vwTAAJZyEaTo"},"execution_count":null,"outputs":[]}],"metadata":{"accelerator":"GPU","colab":{"gpuType":"T4","provenance":[]},"kernelspec":{"display_name":"Python 3","name":"python3"},"language_info":{"name":"python"}},"nbformat":4,"nbformat_minor":0}