Wolverine001/Alexnet_TransferLearning

language: en license: mit datasets: [Cats-Dogs] metrics: [accuracy, f1, precision, recall] ---

🐱🐶 Transfer Learning on AlexNet for Cats vs. Dogs Classification

This model fine-tunes AlexNet using Transfer Learning to classify images into two categories: Cats and Dogs.

📝 Model Details

• —Pre-trained Model: AlexNet
• —Dataset Used: Cats-Dogs
• —Batch Size: 8
• —Learning Rate: 0.001
• —Epochs: 5

📌 Baseline Performance (Before Transfer Learning)

Validation Accuracy: 40.66%

• —Precision: 0.3983
• —Recall: 0.4066
• —F1-score: 0.3942

• —Confusion Matrix: [[659 1841] [1126 1374]] ---

✅ Performance After Training

Training Accuracy: 92.40%

• —Precision: 0.9250
• —Recall: 0.9240
• —F1-score: 0.9240

Confusion Matrix: [[9486 514] [1006 8994]]

Validation Accuracy: 94.10%

• —Precision: 0.9425
• —Recall: 0.9410
• —F1-score: 0.9410

Confusion Matrix: [[2425 75] [ 220 2280]]

You can download the model from Hugging Face.