CifNetForImageClassification(
  (resnet): CifNetModel(
    (embedder): CifNetEmbeddings(
      (embedder): CifNetConvLayer(
        (convolution): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
        (normalization): BatchNorm2d(64, 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): 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): 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()
                )
              )
            )
          )
        )
        (2): CifNetStage(
          (layers): Sequential(
            (0): CifNetBasicLayer(
              (shortcut): CifNetShortCut(
                (convolution): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
                (normalization): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (layer): Sequential(
                (0): CifNetConvLayer(
                  (convolution): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
                (1): CifNetConvLayer(
                  (convolution): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
              )
            )
          )
        )
        (3): CifNetStage(
          (layers): Sequential(
            (0): CifNetBasicLayer(
              (shortcut): CifNetShortCut(
                (convolution): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
                (normalization): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (layer): Sequential(
                (0): CifNetConvLayer(
                  (convolution): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (activation): SiLU()
                )
                (1): CifNetConvLayer(
                  (convolution): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (normalization): BatchNorm2d(512, 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=512, out_features=10, bias=True)
  )
)
----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1          [4, 64, 112, 112]           9,408
       BatchNorm2d-2          [4, 64, 112, 112]             128
              SiLU-3          [4, 64, 112, 112]               0
   CifNetConvLayer-4          [4, 64, 112, 112]               0
         MaxPool2d-5            [4, 64, 56, 56]               0
  CifNetEmbeddings-6            [4, 64, 56, 56]               0
            Conv2d-7            [4, 64, 56, 56]          36,864
       BatchNorm2d-8            [4, 64, 56, 56]             128
              SiLU-9            [4, 64, 56, 56]               0
  CifNetConvLayer-10            [4, 64, 56, 56]               0
           Conv2d-11            [4, 64, 56, 56]          36,864
      BatchNorm2d-12            [4, 64, 56, 56]             128
             SiLU-13            [4, 64, 56, 56]               0
  CifNetConvLayer-14            [4, 64, 56, 56]               0
         Identity-15            [4, 64, 56, 56]               0
 CifNetBasicLayer-16            [4, 64, 56, 56]               0
      CifNetStage-17            [4, 64, 56, 56]               0
           Conv2d-18           [4, 128, 28, 28]          73,728
      BatchNorm2d-19           [4, 128, 28, 28]             256
             SiLU-20           [4, 128, 28, 28]               0
  CifNetConvLayer-21           [4, 128, 28, 28]               0
           Conv2d-22           [4, 128, 28, 28]         147,456
      BatchNorm2d-23           [4, 128, 28, 28]             256
             SiLU-24           [4, 128, 28, 28]               0
  CifNetConvLayer-25           [4, 128, 28, 28]               0
           Conv2d-26           [4, 128, 28, 28]           8,192
      BatchNorm2d-27           [4, 128, 28, 28]             256
   CifNetShortCut-28           [4, 128, 28, 28]               0
 CifNetBasicLayer-29           [4, 128, 28, 28]               0
      CifNetStage-30           [4, 128, 28, 28]               0
           Conv2d-31           [4, 256, 14, 14]         294,912
      BatchNorm2d-32           [4, 256, 14, 14]             512
             SiLU-33           [4, 256, 14, 14]               0
  CifNetConvLayer-34           [4, 256, 14, 14]               0
           Conv2d-35           [4, 256, 14, 14]         589,824
      BatchNorm2d-36           [4, 256, 14, 14]             512
             SiLU-37           [4, 256, 14, 14]               0
  CifNetConvLayer-38           [4, 256, 14, 14]               0
           Conv2d-39           [4, 256, 14, 14]          32,768
      BatchNorm2d-40           [4, 256, 14, 14]             512
   CifNetShortCut-41           [4, 256, 14, 14]               0
 CifNetBasicLayer-42           [4, 256, 14, 14]               0
      CifNetStage-43           [4, 256, 14, 14]               0
           Conv2d-44             [4, 512, 7, 7]       1,179,648
      BatchNorm2d-45             [4, 512, 7, 7]           1,024
             SiLU-46             [4, 512, 7, 7]               0
  CifNetConvLayer-47             [4, 512, 7, 7]               0
           Conv2d-48             [4, 512, 7, 7]       2,359,296
      BatchNorm2d-49             [4, 512, 7, 7]           1,024
             SiLU-50             [4, 512, 7, 7]               0
  CifNetConvLayer-51             [4, 512, 7, 7]               0
           Conv2d-52             [4, 512, 7, 7]         131,072
      BatchNorm2d-53             [4, 512, 7, 7]           1,024
   CifNetShortCut-54             [4, 512, 7, 7]               0
 CifNetBasicLayer-55             [4, 512, 7, 7]               0
      CifNetStage-56             [4, 512, 7, 7]               0
    CifNetEncoder-57          [[-1, 512, 7, 7]]               0
AdaptiveAvgPool2d-58             [4, 512, 1, 1]               0
      CifNetModel-59  [[-1, 512, 7, 7], [-1, 512, 1, 1]]               0
          Flatten-60                   [4, 512]               0
           Linear-61                    [4, 10]           5,130
================================================================
Total params: 4,910,922
Trainable params: 4,910,922
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 2.30
Forward/backward pass size (MB): 345.14
Params size (MB): 18.73
Estimated Total Size (MB): 366.17
----------------------------------------------------------------