CifNetForImageClassification(
  (resnet): CifNetModel(
    (embedder): CifNetEmbeddings(
      (embedder): CifNetConvLayer(
        (convolution): Conv2d(3, 32, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
        (normalization): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (activation): SiLU()
      )
      (pooler): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    )
    (encoder): CifNetEncoder(
      (stages): ModuleList(
        (0): CifNetStage(
          (layers): Sequential(
            (0): CifNetBasicLayer(
              (shortcut): CifNetShortCut(
                (convolution): Conv2d(32, 64, kernel_size=(1, 1), stride=(2, 2), bias=False)
                (normalization): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (layer): Sequential(
                (0): CifNetConvLayer(
                  (convolution): Conv2d(32, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
                (1): CifNetConvLayer(
                  (convolution): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
              )
            )
          )
        )
        (1): CifNetStage(
          (layers): Sequential(
            (0): CifNetBasicLayer(
              (shortcut): Identity()
              (layer): Sequential(
                (0): CifNetConvLayer(
                  (convolution): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
                (1): CifNetConvLayer(
                  (convolution): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
              )
            )
            (1): CifNetBasicLayer(
              (shortcut): Identity()
              (layer): Sequential(
                (0): CifNetConvLayer(
                  (convolution): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
                (1): CifNetConvLayer(
                  (convolution): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
              )
            )
          )
        )
        (2): CifNetStage(
          (layers): Sequential(
            (0): CifNetBasicLayer(
              (shortcut): CifNetShortCut(
                (convolution): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
                (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (layer): Sequential(
                (0): CifNetConvLayer(
                  (convolution): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
                (1): CifNetConvLayer(
                  (convolution): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
              )
            )
            (1): CifNetBasicLayer(
              (shortcut): Identity()
              (layer): Sequential(
                (0): CifNetConvLayer(
                  (convolution): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
                (1): CifNetConvLayer(
                  (convolution): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
              )
            )
          )
        )
        (3): CifNetStage(
          (layers): Sequential(
            (0): CifNetBasicLayer(
              (shortcut): Identity()
              (layer): Sequential(
                (0): CifNetConvLayer(
                  (convolution): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
                (1): CifNetConvLayer(
                  (convolution): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
              )
            )
            (1): CifNetBasicLayer(
              (shortcut): Identity()
              (layer): Sequential(
                (0): CifNetConvLayer(
                  (convolution): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
                (1): CifNetConvLayer(
                  (convolution): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
              )
            )
          )
        )
      )
    )
    (pooler): AdaptiveAvgPool2d(output_size=(1, 1))
  )
  (classifier): Sequential(
    (0): Flatten(start_dim=1, end_dim=-1)
    (1): Linear(in_features=128, out_features=10, bias=True)
  )
)
----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1          [4, 32, 112, 112]           4,704
       BatchNorm2d-2          [4, 32, 112, 112]              64
              SiLU-3          [4, 32, 112, 112]               0
   CifNetConvLayer-4          [4, 32, 112, 112]               0
         MaxPool2d-5            [4, 32, 56, 56]               0
  CifNetEmbeddings-6            [4, 32, 56, 56]               0
            Conv2d-7            [4, 64, 28, 28]          18,432
       BatchNorm2d-8            [4, 64, 28, 28]             128
              SiLU-9            [4, 64, 28, 28]               0
  CifNetConvLayer-10            [4, 64, 28, 28]               0
           Conv2d-11            [4, 64, 28, 28]          36,864
      BatchNorm2d-12            [4, 64, 28, 28]             128
             SiLU-13            [4, 64, 28, 28]               0
  CifNetConvLayer-14            [4, 64, 28, 28]               0
           Conv2d-15            [4, 64, 28, 28]           2,048
      BatchNorm2d-16            [4, 64, 28, 28]             128
   CifNetShortCut-17            [4, 64, 28, 28]               0
 CifNetBasicLayer-18            [4, 64, 28, 28]               0
      CifNetStage-19            [4, 64, 28, 28]               0
           Conv2d-20            [4, 64, 28, 28]          36,864
      BatchNorm2d-21            [4, 64, 28, 28]             128
             SiLU-22            [4, 64, 28, 28]               0
  CifNetConvLayer-23            [4, 64, 28, 28]               0
           Conv2d-24            [4, 64, 28, 28]          36,864
      BatchNorm2d-25            [4, 64, 28, 28]             128
             SiLU-26            [4, 64, 28, 28]               0
  CifNetConvLayer-27            [4, 64, 28, 28]               0
         Identity-28            [4, 64, 28, 28]               0
 CifNetBasicLayer-29            [4, 64, 28, 28]               0
           Conv2d-30            [4, 64, 28, 28]          36,864
      BatchNorm2d-31            [4, 64, 28, 28]             128
             SiLU-32            [4, 64, 28, 28]               0
  CifNetConvLayer-33            [4, 64, 28, 28]               0
           Conv2d-34            [4, 64, 28, 28]          36,864
      BatchNorm2d-35            [4, 64, 28, 28]             128
             SiLU-36            [4, 64, 28, 28]               0
  CifNetConvLayer-37            [4, 64, 28, 28]               0
         Identity-38            [4, 64, 28, 28]               0
 CifNetBasicLayer-39            [4, 64, 28, 28]               0
      CifNetStage-40            [4, 64, 28, 28]               0
           Conv2d-41           [4, 128, 14, 14]          73,728
      BatchNorm2d-42           [4, 128, 14, 14]             256
             SiLU-43           [4, 128, 14, 14]               0
  CifNetConvLayer-44           [4, 128, 14, 14]               0
           Conv2d-45           [4, 128, 14, 14]         147,456
      BatchNorm2d-46           [4, 128, 14, 14]             256
             SiLU-47           [4, 128, 14, 14]               0
  CifNetConvLayer-48           [4, 128, 14, 14]               0
           Conv2d-49           [4, 128, 14, 14]           8,192
      BatchNorm2d-50           [4, 128, 14, 14]             256
   CifNetShortCut-51           [4, 128, 14, 14]               0
 CifNetBasicLayer-52           [4, 128, 14, 14]               0
           Conv2d-53           [4, 128, 14, 14]         147,456
      BatchNorm2d-54           [4, 128, 14, 14]             256
             SiLU-55           [4, 128, 14, 14]               0
  CifNetConvLayer-56           [4, 128, 14, 14]               0
           Conv2d-57           [4, 128, 14, 14]         147,456
      BatchNorm2d-58           [4, 128, 14, 14]             256
             SiLU-59           [4, 128, 14, 14]               0
  CifNetConvLayer-60           [4, 128, 14, 14]               0
         Identity-61           [4, 128, 14, 14]               0
 CifNetBasicLayer-62           [4, 128, 14, 14]               0
      CifNetStage-63           [4, 128, 14, 14]               0
           Conv2d-64           [4, 128, 14, 14]         147,456
      BatchNorm2d-65           [4, 128, 14, 14]             256
             SiLU-66           [4, 128, 14, 14]               0
  CifNetConvLayer-67           [4, 128, 14, 14]               0
           Conv2d-68           [4, 128, 14, 14]         147,456
      BatchNorm2d-69           [4, 128, 14, 14]             256
             SiLU-70           [4, 128, 14, 14]               0
  CifNetConvLayer-71           [4, 128, 14, 14]               0
         Identity-72           [4, 128, 14, 14]               0
 CifNetBasicLayer-73           [4, 128, 14, 14]               0
           Conv2d-74           [4, 128, 14, 14]         147,456
      BatchNorm2d-75           [4, 128, 14, 14]             256
             SiLU-76           [4, 128, 14, 14]               0
  CifNetConvLayer-77           [4, 128, 14, 14]               0
           Conv2d-78           [4, 128, 14, 14]         147,456
      BatchNorm2d-79           [4, 128, 14, 14]             256
             SiLU-80           [4, 128, 14, 14]               0
  CifNetConvLayer-81           [4, 128, 14, 14]               0
         Identity-82           [4, 128, 14, 14]               0
 CifNetBasicLayer-83           [4, 128, 14, 14]               0
      CifNetStage-84           [4, 128, 14, 14]               0
    CifNetEncoder-85        [[-1, 128, 14, 14]]               0
AdaptiveAvgPool2d-86             [4, 128, 1, 1]               0
      CifNetModel-87  [[-1, 128, 14, 14], [-1, 128, 1, 1]]               0
          Flatten-88                   [4, 128]               0
           Linear-89                    [4, 10]           1,290
================================================================
Total params: 1,328,170
Trainable params: 1,328,170
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 2.30
Forward/backward pass size (MB): 165.19
Params size (MB): 5.07
Estimated Total Size (MB): 172.56
----------------------------------------------------------------