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, 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(32, 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): 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()
                )
              )
            )
            (2): 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): 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()
                )
              )
            )
          )
        )
        (2): CifNetStage(
          (layers): Sequential(
            (0): CifNetBasicLayer(
              (shortcut): CifNetShortCut(
                (convolution): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (normalization): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (layer): Sequential(
                (0): CifNetConvLayer(
                  (convolution): Conv2d(128, 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): 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()
                )
              )
            )
            (3): 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()
                )
              )
            )
          )
        )
        (3): 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): 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()
                )
              )
            )
            (3): 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()
                )
              )
            )
          )
        )
      )
    )
    (pooler): AdaptiveAvgPool2d(output_size=(1, 1))
  )
  (classifier): Sequential(
    (0): Flatten(start_dim=1, end_dim=-1)
    (1): Linear(in_features=64, 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, 128, 28, 28]          36,864
       BatchNorm2d-8           [4, 128, 28, 28]             256
              SiLU-9           [4, 128, 28, 28]               0
  CifNetConvLayer-10           [4, 128, 28, 28]               0
           Conv2d-11           [4, 128, 28, 28]         147,456
      BatchNorm2d-12           [4, 128, 28, 28]             256
             SiLU-13           [4, 128, 28, 28]               0
  CifNetConvLayer-14           [4, 128, 28, 28]               0
           Conv2d-15           [4, 128, 28, 28]           4,096
      BatchNorm2d-16           [4, 128, 28, 28]             256
   CifNetShortCut-17           [4, 128, 28, 28]               0
 CifNetBasicLayer-18           [4, 128, 28, 28]               0
      CifNetStage-19           [4, 128, 28, 28]               0
           Conv2d-20           [4, 128, 28, 28]         147,456
      BatchNorm2d-21           [4, 128, 28, 28]             256
             SiLU-22           [4, 128, 28, 28]               0
  CifNetConvLayer-23           [4, 128, 28, 28]               0
           Conv2d-24           [4, 128, 28, 28]         147,456
      BatchNorm2d-25           [4, 128, 28, 28]             256
             SiLU-26           [4, 128, 28, 28]               0
  CifNetConvLayer-27           [4, 128, 28, 28]               0
         Identity-28           [4, 128, 28, 28]               0
 CifNetBasicLayer-29           [4, 128, 28, 28]               0
           Conv2d-30           [4, 128, 28, 28]         147,456
      BatchNorm2d-31           [4, 128, 28, 28]             256
             SiLU-32           [4, 128, 28, 28]               0
  CifNetConvLayer-33           [4, 128, 28, 28]               0
           Conv2d-34           [4, 128, 28, 28]         147,456
      BatchNorm2d-35           [4, 128, 28, 28]             256
             SiLU-36           [4, 128, 28, 28]               0
  CifNetConvLayer-37           [4, 128, 28, 28]               0
         Identity-38           [4, 128, 28, 28]               0
 CifNetBasicLayer-39           [4, 128, 28, 28]               0
           Conv2d-40           [4, 128, 28, 28]         147,456
      BatchNorm2d-41           [4, 128, 28, 28]             256
             SiLU-42           [4, 128, 28, 28]               0
  CifNetConvLayer-43           [4, 128, 28, 28]               0
           Conv2d-44           [4, 128, 28, 28]         147,456
      BatchNorm2d-45           [4, 128, 28, 28]             256
             SiLU-46           [4, 128, 28, 28]               0
  CifNetConvLayer-47           [4, 128, 28, 28]               0
         Identity-48           [4, 128, 28, 28]               0
 CifNetBasicLayer-49           [4, 128, 28, 28]               0
           Conv2d-50           [4, 128, 28, 28]         147,456
      BatchNorm2d-51           [4, 128, 28, 28]             256
             SiLU-52           [4, 128, 28, 28]               0
  CifNetConvLayer-53           [4, 128, 28, 28]               0
           Conv2d-54           [4, 128, 28, 28]         147,456
      BatchNorm2d-55           [4, 128, 28, 28]             256
             SiLU-56           [4, 128, 28, 28]               0
  CifNetConvLayer-57           [4, 128, 28, 28]               0
         Identity-58           [4, 128, 28, 28]               0
 CifNetBasicLayer-59           [4, 128, 28, 28]               0
      CifNetStage-60           [4, 128, 28, 28]               0
           Conv2d-61            [4, 64, 28, 28]          73,728
      BatchNorm2d-62            [4, 64, 28, 28]             128
             SiLU-63            [4, 64, 28, 28]               0
  CifNetConvLayer-64            [4, 64, 28, 28]               0
           Conv2d-65            [4, 64, 28, 28]          36,864
      BatchNorm2d-66            [4, 64, 28, 28]             128
             SiLU-67            [4, 64, 28, 28]               0
  CifNetConvLayer-68            [4, 64, 28, 28]               0
           Conv2d-69            [4, 64, 28, 28]           8,192
      BatchNorm2d-70            [4, 64, 28, 28]             128
   CifNetShortCut-71            [4, 64, 28, 28]               0
 CifNetBasicLayer-72            [4, 64, 28, 28]               0
           Conv2d-73            [4, 64, 28, 28]          36,864
      BatchNorm2d-74            [4, 64, 28, 28]             128
             SiLU-75            [4, 64, 28, 28]               0
  CifNetConvLayer-76            [4, 64, 28, 28]               0
           Conv2d-77            [4, 64, 28, 28]          36,864
      BatchNorm2d-78            [4, 64, 28, 28]             128
             SiLU-79            [4, 64, 28, 28]               0
  CifNetConvLayer-80            [4, 64, 28, 28]               0
         Identity-81            [4, 64, 28, 28]               0
 CifNetBasicLayer-82            [4, 64, 28, 28]               0
           Conv2d-83            [4, 64, 28, 28]          36,864
      BatchNorm2d-84            [4, 64, 28, 28]             128
             SiLU-85            [4, 64, 28, 28]               0
  CifNetConvLayer-86            [4, 64, 28, 28]               0
           Conv2d-87            [4, 64, 28, 28]          36,864
      BatchNorm2d-88            [4, 64, 28, 28]             128
             SiLU-89            [4, 64, 28, 28]               0
  CifNetConvLayer-90            [4, 64, 28, 28]               0
         Identity-91            [4, 64, 28, 28]               0
 CifNetBasicLayer-92            [4, 64, 28, 28]               0
           Conv2d-93            [4, 64, 28, 28]          36,864
      BatchNorm2d-94            [4, 64, 28, 28]             128
             SiLU-95            [4, 64, 28, 28]               0
  CifNetConvLayer-96            [4, 64, 28, 28]               0
           Conv2d-97            [4, 64, 28, 28]          36,864
      BatchNorm2d-98            [4, 64, 28, 28]             128
             SiLU-99            [4, 64, 28, 28]               0
 CifNetConvLayer-100            [4, 64, 28, 28]               0
        Identity-101            [4, 64, 28, 28]               0
CifNetBasicLayer-102            [4, 64, 28, 28]               0
     CifNetStage-103            [4, 64, 28, 28]               0
          Conv2d-104            [4, 64, 28, 28]          36,864
     BatchNorm2d-105            [4, 64, 28, 28]             128
            SiLU-106            [4, 64, 28, 28]               0
 CifNetConvLayer-107            [4, 64, 28, 28]               0
          Conv2d-108            [4, 64, 28, 28]          36,864
     BatchNorm2d-109            [4, 64, 28, 28]             128
            SiLU-110            [4, 64, 28, 28]               0
 CifNetConvLayer-111            [4, 64, 28, 28]               0
        Identity-112            [4, 64, 28, 28]               0
CifNetBasicLayer-113            [4, 64, 28, 28]               0
          Conv2d-114            [4, 64, 28, 28]          36,864
     BatchNorm2d-115            [4, 64, 28, 28]             128
            SiLU-116            [4, 64, 28, 28]               0
 CifNetConvLayer-117            [4, 64, 28, 28]               0
          Conv2d-118            [4, 64, 28, 28]          36,864
     BatchNorm2d-119            [4, 64, 28, 28]             128
            SiLU-120            [4, 64, 28, 28]               0
 CifNetConvLayer-121            [4, 64, 28, 28]               0
        Identity-122            [4, 64, 28, 28]               0
CifNetBasicLayer-123            [4, 64, 28, 28]               0
          Conv2d-124            [4, 64, 28, 28]          36,864
     BatchNorm2d-125            [4, 64, 28, 28]             128
            SiLU-126            [4, 64, 28, 28]               0
 CifNetConvLayer-127            [4, 64, 28, 28]               0
          Conv2d-128            [4, 64, 28, 28]          36,864
     BatchNorm2d-129            [4, 64, 28, 28]             128
            SiLU-130            [4, 64, 28, 28]               0
 CifNetConvLayer-131            [4, 64, 28, 28]               0
        Identity-132            [4, 64, 28, 28]               0
CifNetBasicLayer-133            [4, 64, 28, 28]               0
          Conv2d-134            [4, 64, 28, 28]          36,864
     BatchNorm2d-135            [4, 64, 28, 28]             128
            SiLU-136            [4, 64, 28, 28]               0
 CifNetConvLayer-137            [4, 64, 28, 28]               0
          Conv2d-138            [4, 64, 28, 28]          36,864
     BatchNorm2d-139            [4, 64, 28, 28]             128
            SiLU-140            [4, 64, 28, 28]               0
 CifNetConvLayer-141            [4, 64, 28, 28]               0
        Identity-142            [4, 64, 28, 28]               0
CifNetBasicLayer-143            [4, 64, 28, 28]               0
     CifNetStage-144            [4, 64, 28, 28]               0
   CifNetEncoder-145         [[-1, 64, 28, 28]]               0
AdaptiveAvgPool2d-146              [4, 64, 1, 1]               0
     CifNetModel-147  [[-1, 64, 28, 28], [-1, 64, 1, 1]]               0
         Flatten-148                    [4, 64]               0
          Linear-149                    [4, 10]             650
================================================================
Total params: 2,013,354
Trainable params: 2,013,354
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 2.30
Forward/backward pass size (MB): 373.25
Params size (MB): 7.68
Estimated Total Size (MB): 383.22
----------------------------------------------------------------