| 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): Identity() |
| (layer): Sequential( |
| (0): CifNetConvLayer( |
| (convolution): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) |
| (normalization): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) |
| (activation): SiLU() |
| ) |
| (1): CifNetConvLayer( |
| (convolution): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) |
| (normalization): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) |
| (activation): SiLU() |
| ) |
| ) |
| ) |
| ) |
| ) |
| (1): 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() |
| ) |
| ) |
| ) |
| ) |
| ) |
| (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): 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() |
| ) |
| ) |
| ) |
| (3): 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, 32, 56, 56] 9,216 |
| BatchNorm2d-8 [4, 32, 56, 56] 64 |
| SiLU-9 [4, 32, 56, 56] 0 |
| CifNetConvLayer-10 [4, 32, 56, 56] 0 |
| Conv2d-11 [4, 32, 56, 56] 9,216 |
| BatchNorm2d-12 [4, 32, 56, 56] 64 |
| SiLU-13 [4, 32, 56, 56] 0 |
| CifNetConvLayer-14 [4, 32, 56, 56] 0 |
| Identity-15 [4, 32, 56, 56] 0 |
| CifNetBasicLayer-16 [4, 32, 56, 56] 0 |
| CifNetStage-17 [4, 32, 56, 56] 0 |
| Conv2d-18 [4, 64, 28, 28] 18,432 |
| BatchNorm2d-19 [4, 64, 28, 28] 128 |
| SiLU-20 [4, 64, 28, 28] 0 |
| CifNetConvLayer-21 [4, 64, 28, 28] 0 |
| Conv2d-22 [4, 64, 28, 28] 36,864 |
| BatchNorm2d-23 [4, 64, 28, 28] 128 |
| SiLU-24 [4, 64, 28, 28] 0 |
| CifNetConvLayer-25 [4, 64, 28, 28] 0 |
| Conv2d-26 [4, 64, 28, 28] 2,048 |
| BatchNorm2d-27 [4, 64, 28, 28] 128 |
| CifNetShortCut-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 |
| 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 |
| CifNetStage-73 [4, 128, 14, 14] 0 |
| Conv2d-74 [4, 256, 7, 7] 294,912 |
| BatchNorm2d-75 [4, 256, 7, 7] 512 |
| SiLU-76 [4, 256, 7, 7] 0 |
| CifNetConvLayer-77 [4, 256, 7, 7] 0 |
| Conv2d-78 [4, 256, 7, 7] 589,824 |
| BatchNorm2d-79 [4, 256, 7, 7] 512 |
| SiLU-80 [4, 256, 7, 7] 0 |
| CifNetConvLayer-81 [4, 256, 7, 7] 0 |
| Conv2d-82 [4, 256, 7, 7] 32,768 |
| BatchNorm2d-83 [4, 256, 7, 7] 512 |
| CifNetShortCut-84 [4, 256, 7, 7] 0 |
| CifNetBasicLayer-85 [4, 256, 7, 7] 0 |
| Conv2d-86 [4, 256, 7, 7] 589,824 |
| BatchNorm2d-87 [4, 256, 7, 7] 512 |
| SiLU-88 [4, 256, 7, 7] 0 |
| CifNetConvLayer-89 [4, 256, 7, 7] 0 |
| Conv2d-90 [4, 256, 7, 7] 589,824 |
| BatchNorm2d-91 [4, 256, 7, 7] 512 |
| SiLU-92 [4, 256, 7, 7] 0 |
| CifNetConvLayer-93 [4, 256, 7, 7] 0 |
| Identity-94 [4, 256, 7, 7] 0 |
| CifNetBasicLayer-95 [4, 256, 7, 7] 0 |
| Conv2d-96 [4, 256, 7, 7] 589,824 |
| BatchNorm2d-97 [4, 256, 7, 7] 512 |
| SiLU-98 [4, 256, 7, 7] 0 |
| CifNetConvLayer-99 [4, 256, 7, 7] 0 |
| Conv2d-100 [4, 256, 7, 7] 589,824 |
| BatchNorm2d-101 [4, 256, 7, 7] 512 |
| SiLU-102 [4, 256, 7, 7] 0 |
| CifNetConvLayer-103 [4, 256, 7, 7] 0 |
| Identity-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 |
| CifNetStage-116 [4, 256, 7, 7] 0 |
| CifNetEncoder-117 [[-1, 256, 7, 7]] 0 |
| AdaptiveAvgPool2d-118 [4, 256, 1, 1] 0 |
| CifNetModel-119 [[-1, 256, 7, 7], [-1, 256, 1, 1]] 0 |
| Flatten-120 [4, 256] 0 |
| Linear-121 [4, 10] 2,570 |
| ================================================================ |
| Total params: 5,439,658 |
| Trainable params: 5,439,658 |
| Non-trainable params: 0 |
| ---------------------------------------------------------------- |
| Input size (MB): 2.30 |
| Forward/backward pass size (MB): 190.18 |
| Params size (MB): 20.75 |
| Estimated Total Size (MB): 213.23 |
| ---------------------------------------------------------------- |
|
|
