AlirezaF138/KNTU-VC-4022-License-Plate-Recognition

• —Model: "functional_1"
• —Layer (type) ┃ Output Shape ┃ Param # ┃
• —input_layer (InputLayer) │ (None, 256, 256, 3) │ 0 │
• —conv2d (Conv2D) │ (None, 256, 256, 32) │ 4,736 │
• —conv2d_1 (Conv2D) │ (None, 256, 256, 32) │ 50,208 │
• —max_pooling2d (MaxPooling2D) │ (None, 64, 64, 32) │ 0 │
• —conv2d_2 (Conv2D) │ (None, 64, 64, 64) │ 51,264 │
• —conv2d_3 (Conv2D) │ (None, 64, 64, 64) │ 102,464 │
• —maxpooling2d1 (MaxPooling2D) │ (None, 32, 32, 64) │ 0 │
• —conv2d_4 (Conv2D) │ (None, 32, 32, 128) │ 73,856 │
• —conv2d_5 (Conv2D) │ (None, 32, 32, 128) │ 147,584 │
• —maxpooling2d2 (MaxPooling2D) │ (None, 16, 16, 128) │ 0 │
• —conv2d_6 (Conv2D) │ (None, 16, 16, 256) │ 295,168 │
• —conv2d_7 (Conv2D) │ (None, 16, 16, 256) │ 590,080 │
• —maxpooling2d3 (MaxPooling2D) │ (None, 8, 8, 256) │ 0 │
• —flatten (Flatten) │ (None, 16384) │ 0 │
• —dense (Dense) │ (None, 1024) │ 16,778,240 │
• —dense_1 (Dense) │ (None, 512) │ 524,800 │
• —dense_2 (Dense) │ (None, 256) │ 131,328 │
• —dense_3 (Dense) │ (None, 128) │ 32,896 │
• —dense_4 (Dense) │ (None, 8) │ 1,032 │
• —Total params: 56,350,970 (214.96 MB)
• —Trainable params: 18,783,656 (71.65 MB)
• —Non-trainable params: 0 (0.00 B)
• —Optimizer params: 37,567,314 (143.31 MB)

Test Loss: 0.001258564880117774, Test MAE: 0.018795978277921677