| 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): 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): 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() | |
| ) | |
| ) | |
| ) | |
| (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() | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (3): 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() | |
| ) | |
| ) | |
| ) | |
| (1): CifNetBasicLayer( | |
| (shortcut): Identity() | |
| (layer): Sequential( | |
| (0): 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() | |
| ) | |
| (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() | |
| ) | |
| ) | |
| ) | |
| (2): CifNetBasicLayer( | |
| (shortcut): Identity() | |
| (layer): Sequential( | |
| (0): 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() | |
| ) | |
| (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() | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (pooler): AdaptiveAvgPool2d(output_size=(1, 1)) | |
| ) | |
| (classifier): Sequential( | |
| (0): Flatten(start_dim=1, end_dim=-1) | |
| (1): Linear(in_features=256, 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 | |
| Conv2d-19 [4, 64, 28, 28] 36,864 | |
| BatchNorm2d-20 [4, 64, 28, 28] 128 | |
| SiLU-21 [4, 64, 28, 28] 0 | |
| CifNetConvLayer-22 [4, 64, 28, 28] 0 | |
| Conv2d-23 [4, 64, 28, 28] 36,864 | |
| BatchNorm2d-24 [4, 64, 28, 28] 128 | |
| SiLU-25 [4, 64, 28, 28] 0 | |
| CifNetConvLayer-26 [4, 64, 28, 28] 0 | |
| Identity-27 [4, 64, 28, 28] 0 | |
| CifNetBasicLayer-28 [4, 64, 28, 28] 0 | |
| CifNetStage-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 | |
| Conv2d-40 [4, 64, 28, 28] 36,864 | |
| BatchNorm2d-41 [4, 64, 28, 28] 128 | |
| SiLU-42 [4, 64, 28, 28] 0 | |
| CifNetConvLayer-43 [4, 64, 28, 28] 0 | |
| Conv2d-44 [4, 64, 28, 28] 36,864 | |
| BatchNorm2d-45 [4, 64, 28, 28] 128 | |
| SiLU-46 [4, 64, 28, 28] 0 | |
| CifNetConvLayer-47 [4, 64, 28, 28] 0 | |
| Identity-48 [4, 64, 28, 28] 0 | |
| CifNetBasicLayer-49 [4, 64, 28, 28] 0 | |
| CifNetStage-50 [4, 64, 28, 28] 0 | |
| Conv2d-51 [4, 128, 14, 14] 73,728 | |
| BatchNorm2d-52 [4, 128, 14, 14] 256 | |
| SiLU-53 [4, 128, 14, 14] 0 | |
| CifNetConvLayer-54 [4, 128, 14, 14] 0 | |
| Conv2d-55 [4, 128, 14, 14] 147,456 | |
| BatchNorm2d-56 [4, 128, 14, 14] 256 | |
| SiLU-57 [4, 128, 14, 14] 0 | |
| CifNetConvLayer-58 [4, 128, 14, 14] 0 | |
| Conv2d-59 [4, 128, 14, 14] 8,192 | |
| BatchNorm2d-60 [4, 128, 14, 14] 256 | |
| CifNetShortCut-61 [4, 128, 14, 14] 0 | |
| CifNetBasicLayer-62 [4, 128, 14, 14] 0 | |
| Conv2d-63 [4, 128, 14, 14] 147,456 | |
| BatchNorm2d-64 [4, 128, 14, 14] 256 | |
| SiLU-65 [4, 128, 14, 14] 0 | |
| CifNetConvLayer-66 [4, 128, 14, 14] 0 | |
| Conv2d-67 [4, 128, 14, 14] 147,456 | |
| BatchNorm2d-68 [4, 128, 14, 14] 256 | |
| SiLU-69 [4, 128, 14, 14] 0 | |
| CifNetConvLayer-70 [4, 128, 14, 14] 0 | |
| Identity-71 [4, 128, 14, 14] 0 | |
| CifNetBasicLayer-72 [4, 128, 14, 14] 0 | |
| Conv2d-73 [4, 128, 14, 14] 147,456 | |
| BatchNorm2d-74 [4, 128, 14, 14] 256 | |
| SiLU-75 [4, 128, 14, 14] 0 | |
| CifNetConvLayer-76 [4, 128, 14, 14] 0 | |
| Conv2d-77 [4, 128, 14, 14] 147,456 | |
| BatchNorm2d-78 [4, 128, 14, 14] 256 | |
| SiLU-79 [4, 128, 14, 14] 0 | |
| CifNetConvLayer-80 [4, 128, 14, 14] 0 | |
| Identity-81 [4, 128, 14, 14] 0 | |
| CifNetBasicLayer-82 [4, 128, 14, 14] 0 | |
| Conv2d-83 [4, 128, 14, 14] 147,456 | |
| BatchNorm2d-84 [4, 128, 14, 14] 256 | |
| SiLU-85 [4, 128, 14, 14] 0 | |
| CifNetConvLayer-86 [4, 128, 14, 14] 0 | |
| Conv2d-87 [4, 128, 14, 14] 147,456 | |
| BatchNorm2d-88 [4, 128, 14, 14] 256 | |
| SiLU-89 [4, 128, 14, 14] 0 | |
| CifNetConvLayer-90 [4, 128, 14, 14] 0 | |
| Identity-91 [4, 128, 14, 14] 0 | |
| CifNetBasicLayer-92 [4, 128, 14, 14] 0 | |
| CifNetStage-93 [4, 128, 14, 14] 0 | |
| Conv2d-94 [4, 256, 7, 7] 294,912 | |
| BatchNorm2d-95 [4, 256, 7, 7] 512 | |
| SiLU-96 [4, 256, 7, 7] 0 | |
| CifNetConvLayer-97 [4, 256, 7, 7] 0 | |
| Conv2d-98 [4, 256, 7, 7] 589,824 | |
| BatchNorm2d-99 [4, 256, 7, 7] 512 | |
| SiLU-100 [4, 256, 7, 7] 0 | |
| CifNetConvLayer-101 [4, 256, 7, 7] 0 | |
| Conv2d-102 [4, 256, 7, 7] 32,768 | |
| BatchNorm2d-103 [4, 256, 7, 7] 512 | |
| CifNetShortCut-104 [4, 256, 7, 7] 0 | |
| CifNetBasicLayer-105 [4, 256, 7, 7] 0 | |
| Conv2d-106 [4, 256, 7, 7] 589,824 | |
| BatchNorm2d-107 [4, 256, 7, 7] 512 | |
| SiLU-108 [4, 256, 7, 7] 0 | |
| CifNetConvLayer-109 [4, 256, 7, 7] 0 | |
| Conv2d-110 [4, 256, 7, 7] 589,824 | |
| BatchNorm2d-111 [4, 256, 7, 7] 512 | |
| SiLU-112 [4, 256, 7, 7] 0 | |
| CifNetConvLayer-113 [4, 256, 7, 7] 0 | |
| Identity-114 [4, 256, 7, 7] 0 | |
| CifNetBasicLayer-115 [4, 256, 7, 7] 0 | |
| Conv2d-116 [4, 256, 7, 7] 589,824 | |
| BatchNorm2d-117 [4, 256, 7, 7] 512 | |
| SiLU-118 [4, 256, 7, 7] 0 | |
| CifNetConvLayer-119 [4, 256, 7, 7] 0 | |
| Conv2d-120 [4, 256, 7, 7] 589,824 | |
| BatchNorm2d-121 [4, 256, 7, 7] 512 | |
| SiLU-122 [4, 256, 7, 7] 0 | |
| CifNetConvLayer-123 [4, 256, 7, 7] 0 | |
| Identity-124 [4, 256, 7, 7] 0 | |
| CifNetBasicLayer-125 [4, 256, 7, 7] 0 | |
| CifNetStage-126 [4, 256, 7, 7] 0 | |
| CifNetEncoder-127 [[-1, 256, 7, 7]] 0 | |
| AdaptiveAvgPool2d-128 [4, 256, 1, 1] 0 | |
| CifNetModel-129 [[-1, 256, 7, 7], [-1, 256, 1, 1]] 0 | |
| Flatten-130 [4, 256] 0 | |
| Linear-131 [4, 10] 2,570 | |
| ================================================================ | |
| Total params: 4,683,818 | |
| Trainable params: 4,683,818 | |
| Non-trainable params: 0 | |
| ---------------------------------------------------------------- | |
| Input size (MB): 2.30 | |
| Forward/backward pass size (MB): 192.47 | |
| Params size (MB): 17.87 | |
| Estimated Total Size (MB): 212.64 | |
| ---------------------------------------------------------------- | |