===========================================================================================================================================================
Layer (type:depth-idx) Input Shape Output Shape Param # Trainable
===========================================================================================================================================================
EfficientNet [32, 3, 224, 224] [32, 1000] -- True
├─Sequential: 1-1 [32, 3, 224, 224] [32, 1280, 7, 7] -- True
│ └─Conv2dNormActivation: 2-1 [32, 3, 224, 224] [32, 32, 112, 112] -- True
│ │ └─Conv2d: 3-1 [32, 3, 224, 224] [32, 32, 112, 112] 864 True
│ │ └─BatchNorm2d: 3-2 [32, 32, 112, 112] [32, 32, 112, 112] 64 True
│ │ └─SiLU: 3-3 [32, 32, 112, 112] [32, 32, 112, 112] -- --
│ └─Sequential: 2-2 [32, 32, 112, 112] [32, 16, 112, 112] -- True
│ │ └─MBConv: 3-4 [32, 32, 112, 112] [32, 16, 112, 112] 1,448 True
│ │ └─MBConv: 3-5 [32, 16, 112, 112] [32, 16, 112, 112] 612 True
│ └─Sequential: 2-3 [32, 16, 112, 112] [32, 24, 56, 56] -- True
│ │ └─MBConv: 3-6 [32, 16, 112, 112] [32, 24, 56, 56] 6,004 True
│ │ └─MBConv: 3-7 [32, 24, 56, 56] [32, 24, 56, 56] 10,710 True
│ │ └─MBConv: 3-8 [32, 24, 56, 56] [32, 24, 56, 56] 10,710 True
│ └─Sequential: 2-4 [32, 24, 56, 56] [32, 40, 28, 28] -- True
│ │ └─MBConv: 3-9 [32, 24, 56, 56] [32, 40, 28, 28] 15,350 True
│ │ └─MBConv: 3-10 [32, 40, 28, 28] [32, 40, 28, 28] 31,290 True
│ │ └─MBConv: 3-11 [32, 40, 28, 28] [32, 40, 28, 28] 31,290 True
│ └─Sequential: 2-5 [32, 40, 28, 28] [32, 80, 14, 14] -- True
│ │ └─MBConv: 3-12 [32, 40, 28, 28] [32, 80, 14, 14] 37,130 True
│ │ └─MBConv: 3-13 [32, 80, 14, 14] [32, 80, 14, 14] 102,900 True
│ │ └─MBConv: 3-14 [32, 80, 14, 14] [32, 80, 14, 14] 102,900 True
│ │ └─MBConv: 3-15 [32, 80, 14, 14] [32, 80, 14, 14] 102,900 True
│ └─Sequential: 2-6 [32, 80, 14, 14] [32, 112, 14, 14] -- True
│ │ └─MBConv: 3-16 [32, 80, 14, 14] [32, 112, 14, 14] 126,004 True
│ │ └─MBConv: 3-17 [32, 112, 14, 14] [32, 112, 14, 14] 208,572 True
│ │ └─MBConv: 3-18 [32, 112, 14, 14] [32, 112, 14, 14] 208,572 True
│ │ └─MBConv: 3-19 [32, 112, 14, 14] [32, 112, 14, 14] 208,572 True
│ └─Sequential: 2-7 [32, 112, 14, 14] [32, 192, 7, 7] -- True
│ │ └─MBConv: 3-20 [32, 112, 14, 14] [32, 192, 7, 7] 262,492 True
│ │ └─MBConv: 3-21 [32, 192, 7, 7] [32, 192, 7, 7] 587,952 True
│ │ └─MBConv: 3-22 [32, 192, 7, 7] [32, 192, 7, 7] 587,952 True
│ │ └─MBConv: 3-23 [32, 192, 7, 7] [32, 192, 7, 7] 587,952 True
│ │ └─MBConv: 3-24 [32, 192, 7, 7] [32, 192, 7, 7] 587,952 True
│ └─Sequential: 2-8 [32, 192, 7, 7] [32, 320, 7, 7] -- True
│ │ └─MBConv: 3-25 [32, 192, 7, 7] [32, 320, 7, 7] 717,232 True
│ │ └─MBConv: 3-26 [32, 320, 7, 7] [32, 320, 7, 7] 1,563,600 True
│ └─Conv2dNormActivation: 2-9 [32, 320, 7, 7] [32, 1280, 7, 7] -- True
│ │ └─Conv2d: 3-27 [32, 320, 7, 7] [32, 1280, 7, 7] 409,600 True
│ │ └─BatchNorm2d: 3-28 [32, 1280, 7, 7] [32, 1280, 7, 7] 2,560 True
│ │ └─SiLU: 3-29 [32, 1280, 7, 7] [32, 1280, 7, 7] -- --
├─AdaptiveAvgPool2d: 1-2 [32, 1280, 7, 7] [32, 1280, 1, 1] -- --
├─Sequential: 1-3 [32, 1280] [32, 1000] -- True
│ └─Dropout: 2-10 [32, 1280] [32, 1280] -- --
│ └─Linear: 2-11 [32, 1280] [32, 1000] 1,281,000 True
===========================================================================================================================================================
Total params: 7,794,184
Trainable params: 7,794,184
Non-trainable params: 0
Total mult-adds (G): 18.23
===========================================================================================================================================================
Input size (MB): 19.27
Forward/backward pass size (MB): 4786.26
Params size (MB): 31.18
Estimated Total Size (MB): 4836.70
===========================================================================================================================================================