ermu2001's picture
Upload folder using huggingface_hub
b410f90 verified
raw
history blame
26.3 kB
CifNetForImageClassification(
(resnet): CifNetModel(
(embedder): CifNetEmbeddings(
(embedder): CifNetConvLayer(
(convolution): Conv2d(3, 16, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(normalization): BatchNorm2d(16, 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(16, 32, kernel_size=(1, 1), stride=(2, 2), bias=False)
(normalization): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(layer): Sequential(
(0): CifNetConvLayer(
(convolution): Conv2d(16, 32, kernel_size=(3, 3), stride=(2, 2), 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): 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()
)
)
)
(2): 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()
)
)
)
(3): 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): 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()
)
)
)
(4): 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()
)
)
)
(5): 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()
)
)
)
(6): 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()
)
)
)
(7): 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, 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(64, 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, 16, 112, 112] 2,352
BatchNorm2d-2 [4, 16, 112, 112] 32
SiLU-3 [4, 16, 112, 112] 0
CifNetConvLayer-4 [4, 16, 112, 112] 0
MaxPool2d-5 [4, 16, 56, 56] 0
CifNetEmbeddings-6 [4, 16, 56, 56] 0
Conv2d-7 [4, 32, 28, 28] 4,608
BatchNorm2d-8 [4, 32, 28, 28] 64
SiLU-9 [4, 32, 28, 28] 0
CifNetConvLayer-10 [4, 32, 28, 28] 0
Conv2d-11 [4, 32, 28, 28] 9,216
BatchNorm2d-12 [4, 32, 28, 28] 64
SiLU-13 [4, 32, 28, 28] 0
CifNetConvLayer-14 [4, 32, 28, 28] 0
Conv2d-15 [4, 32, 28, 28] 512
BatchNorm2d-16 [4, 32, 28, 28] 64
CifNetShortCut-17 [4, 32, 28, 28] 0
CifNetBasicLayer-18 [4, 32, 28, 28] 0
Conv2d-19 [4, 32, 28, 28] 9,216
BatchNorm2d-20 [4, 32, 28, 28] 64
SiLU-21 [4, 32, 28, 28] 0
CifNetConvLayer-22 [4, 32, 28, 28] 0
Conv2d-23 [4, 32, 28, 28] 9,216
BatchNorm2d-24 [4, 32, 28, 28] 64
SiLU-25 [4, 32, 28, 28] 0
CifNetConvLayer-26 [4, 32, 28, 28] 0
Identity-27 [4, 32, 28, 28] 0
CifNetBasicLayer-28 [4, 32, 28, 28] 0
Conv2d-29 [4, 32, 28, 28] 9,216
BatchNorm2d-30 [4, 32, 28, 28] 64
SiLU-31 [4, 32, 28, 28] 0
CifNetConvLayer-32 [4, 32, 28, 28] 0
Conv2d-33 [4, 32, 28, 28] 9,216
BatchNorm2d-34 [4, 32, 28, 28] 64
SiLU-35 [4, 32, 28, 28] 0
CifNetConvLayer-36 [4, 32, 28, 28] 0
Identity-37 [4, 32, 28, 28] 0
CifNetBasicLayer-38 [4, 32, 28, 28] 0
Conv2d-39 [4, 32, 28, 28] 9,216
BatchNorm2d-40 [4, 32, 28, 28] 64
SiLU-41 [4, 32, 28, 28] 0
CifNetConvLayer-42 [4, 32, 28, 28] 0
Conv2d-43 [4, 32, 28, 28] 9,216
BatchNorm2d-44 [4, 32, 28, 28] 64
SiLU-45 [4, 32, 28, 28] 0
CifNetConvLayer-46 [4, 32, 28, 28] 0
Identity-47 [4, 32, 28, 28] 0
CifNetBasicLayer-48 [4, 32, 28, 28] 0
CifNetStage-49 [4, 32, 28, 28] 0
Conv2d-50 [4, 64, 14, 14] 18,432
BatchNorm2d-51 [4, 64, 14, 14] 128
SiLU-52 [4, 64, 14, 14] 0
CifNetConvLayer-53 [4, 64, 14, 14] 0
Conv2d-54 [4, 64, 14, 14] 36,864
BatchNorm2d-55 [4, 64, 14, 14] 128
SiLU-56 [4, 64, 14, 14] 0
CifNetConvLayer-57 [4, 64, 14, 14] 0
Conv2d-58 [4, 64, 14, 14] 2,048
BatchNorm2d-59 [4, 64, 14, 14] 128
CifNetShortCut-60 [4, 64, 14, 14] 0
CifNetBasicLayer-61 [4, 64, 14, 14] 0
Conv2d-62 [4, 64, 14, 14] 36,864
BatchNorm2d-63 [4, 64, 14, 14] 128
SiLU-64 [4, 64, 14, 14] 0
CifNetConvLayer-65 [4, 64, 14, 14] 0
Conv2d-66 [4, 64, 14, 14] 36,864
BatchNorm2d-67 [4, 64, 14, 14] 128
SiLU-68 [4, 64, 14, 14] 0
CifNetConvLayer-69 [4, 64, 14, 14] 0
Identity-70 [4, 64, 14, 14] 0
CifNetBasicLayer-71 [4, 64, 14, 14] 0
Conv2d-72 [4, 64, 14, 14] 36,864
BatchNorm2d-73 [4, 64, 14, 14] 128
SiLU-74 [4, 64, 14, 14] 0
CifNetConvLayer-75 [4, 64, 14, 14] 0
Conv2d-76 [4, 64, 14, 14] 36,864
BatchNorm2d-77 [4, 64, 14, 14] 128
SiLU-78 [4, 64, 14, 14] 0
CifNetConvLayer-79 [4, 64, 14, 14] 0
Identity-80 [4, 64, 14, 14] 0
CifNetBasicLayer-81 [4, 64, 14, 14] 0
Conv2d-82 [4, 64, 14, 14] 36,864
BatchNorm2d-83 [4, 64, 14, 14] 128
SiLU-84 [4, 64, 14, 14] 0
CifNetConvLayer-85 [4, 64, 14, 14] 0
Conv2d-86 [4, 64, 14, 14] 36,864
BatchNorm2d-87 [4, 64, 14, 14] 128
SiLU-88 [4, 64, 14, 14] 0
CifNetConvLayer-89 [4, 64, 14, 14] 0
Identity-90 [4, 64, 14, 14] 0
CifNetBasicLayer-91 [4, 64, 14, 14] 0
Conv2d-92 [4, 64, 14, 14] 36,864
BatchNorm2d-93 [4, 64, 14, 14] 128
SiLU-94 [4, 64, 14, 14] 0
CifNetConvLayer-95 [4, 64, 14, 14] 0
Conv2d-96 [4, 64, 14, 14] 36,864
BatchNorm2d-97 [4, 64, 14, 14] 128
SiLU-98 [4, 64, 14, 14] 0
CifNetConvLayer-99 [4, 64, 14, 14] 0
Identity-100 [4, 64, 14, 14] 0
CifNetBasicLayer-101 [4, 64, 14, 14] 0
Conv2d-102 [4, 64, 14, 14] 36,864
BatchNorm2d-103 [4, 64, 14, 14] 128
SiLU-104 [4, 64, 14, 14] 0
CifNetConvLayer-105 [4, 64, 14, 14] 0
Conv2d-106 [4, 64, 14, 14] 36,864
BatchNorm2d-107 [4, 64, 14, 14] 128
SiLU-108 [4, 64, 14, 14] 0
CifNetConvLayer-109 [4, 64, 14, 14] 0
Identity-110 [4, 64, 14, 14] 0
CifNetBasicLayer-111 [4, 64, 14, 14] 0
Conv2d-112 [4, 64, 14, 14] 36,864
BatchNorm2d-113 [4, 64, 14, 14] 128
SiLU-114 [4, 64, 14, 14] 0
CifNetConvLayer-115 [4, 64, 14, 14] 0
Conv2d-116 [4, 64, 14, 14] 36,864
BatchNorm2d-117 [4, 64, 14, 14] 128
SiLU-118 [4, 64, 14, 14] 0
CifNetConvLayer-119 [4, 64, 14, 14] 0
Identity-120 [4, 64, 14, 14] 0
CifNetBasicLayer-121 [4, 64, 14, 14] 0
Conv2d-122 [4, 64, 14, 14] 36,864
BatchNorm2d-123 [4, 64, 14, 14] 128
SiLU-124 [4, 64, 14, 14] 0
CifNetConvLayer-125 [4, 64, 14, 14] 0
Conv2d-126 [4, 64, 14, 14] 36,864
BatchNorm2d-127 [4, 64, 14, 14] 128
SiLU-128 [4, 64, 14, 14] 0
CifNetConvLayer-129 [4, 64, 14, 14] 0
Identity-130 [4, 64, 14, 14] 0
CifNetBasicLayer-131 [4, 64, 14, 14] 0
CifNetStage-132 [4, 64, 14, 14] 0
Conv2d-133 [4, 256, 7, 7] 147,456
BatchNorm2d-134 [4, 256, 7, 7] 512
SiLU-135 [4, 256, 7, 7] 0
CifNetConvLayer-136 [4, 256, 7, 7] 0
Conv2d-137 [4, 256, 7, 7] 589,824
BatchNorm2d-138 [4, 256, 7, 7] 512
SiLU-139 [4, 256, 7, 7] 0
CifNetConvLayer-140 [4, 256, 7, 7] 0
Conv2d-141 [4, 256, 7, 7] 16,384
BatchNorm2d-142 [4, 256, 7, 7] 512
CifNetShortCut-143 [4, 256, 7, 7] 0
CifNetBasicLayer-144 [4, 256, 7, 7] 0
Conv2d-145 [4, 256, 7, 7] 589,824
BatchNorm2d-146 [4, 256, 7, 7] 512
SiLU-147 [4, 256, 7, 7] 0
CifNetConvLayer-148 [4, 256, 7, 7] 0
Conv2d-149 [4, 256, 7, 7] 589,824
BatchNorm2d-150 [4, 256, 7, 7] 512
SiLU-151 [4, 256, 7, 7] 0
CifNetConvLayer-152 [4, 256, 7, 7] 0
Identity-153 [4, 256, 7, 7] 0
CifNetBasicLayer-154 [4, 256, 7, 7] 0
Conv2d-155 [4, 256, 7, 7] 589,824
BatchNorm2d-156 [4, 256, 7, 7] 512
SiLU-157 [4, 256, 7, 7] 0
CifNetConvLayer-158 [4, 256, 7, 7] 0
Conv2d-159 [4, 256, 7, 7] 589,824
BatchNorm2d-160 [4, 256, 7, 7] 512
SiLU-161 [4, 256, 7, 7] 0
CifNetConvLayer-162 [4, 256, 7, 7] 0
Identity-163 [4, 256, 7, 7] 0
CifNetBasicLayer-164 [4, 256, 7, 7] 0
Conv2d-165 [4, 256, 7, 7] 589,824
BatchNorm2d-166 [4, 256, 7, 7] 512
SiLU-167 [4, 256, 7, 7] 0
CifNetConvLayer-168 [4, 256, 7, 7] 0
Conv2d-169 [4, 256, 7, 7] 589,824
BatchNorm2d-170 [4, 256, 7, 7] 512
SiLU-171 [4, 256, 7, 7] 0
CifNetConvLayer-172 [4, 256, 7, 7] 0
Identity-173 [4, 256, 7, 7] 0
CifNetBasicLayer-174 [4, 256, 7, 7] 0
CifNetStage-175 [4, 256, 7, 7] 0
CifNetEncoder-176 [[-1, 256, 7, 7]] 0
AdaptiveAvgPool2d-177 [4, 256, 1, 1] 0
CifNetModel-178 [[-1, 256, 7, 7], [-1, 256, 1, 1]] 0
Flatten-179 [4, 256] 0
Linear-180 [4, 10] 2,570
================================================================
Total params: 4,947,994
Trainable params: 4,947,994
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 2.30
Forward/backward pass size (MB): 133.14
Params size (MB): 18.88
Estimated Total Size (MB): 154.31
----------------------------------------------------------------