Created
August 25, 2022 09:26
-
-
Save sadimanna/924b0007303438372afccc32aaf5576e to your computer and use it in GitHub Desktop.
Output from torchinfo.summary on ResNet18 for input of (3,224,224)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ===================================================================================================================================================================== | |
| Layer (type:depth-idx) Input Shape Output Shape Param # Kernel Shape Mult-Adds | |
| ===================================================================================================================================================================== | |
| ResNet [1, 3, 224, 224] [1, 1000] -- -- -- | |
| ├─Conv2d: 1-1 [1, 3, 224, 224] [1, 64, 112, 112] 9,408 [7, 7] 118,013,952 | |
| ├─BatchNorm2d: 1-2 [1, 64, 112, 112] [1, 64, 112, 112] 128 -- 128 | |
| ├─ReLU: 1-3 [1, 64, 112, 112] [1, 64, 112, 112] -- -- -- | |
| ├─MaxPool2d: 1-4 [1, 64, 112, 112] [1, 64, 56, 56] -- 3 -- | |
| ├─Sequential: 1-5 [1, 64, 56, 56] [1, 64, 56, 56] -- -- -- | |
| │ └─BasicBlock: 2-1 [1, 64, 56, 56] [1, 64, 56, 56] -- -- -- | |
| │ │ └─Conv2d: 3-1 [1, 64, 56, 56] [1, 64, 56, 56] 36,864 [3, 3] 115,605,504 | |
| │ │ └─BatchNorm2d: 3-2 [1, 64, 56, 56] [1, 64, 56, 56] 128 -- 128 | |
| │ │ └─ReLU: 3-3 [1, 64, 56, 56] [1, 64, 56, 56] -- -- -- | |
| │ │ └─Conv2d: 3-4 [1, 64, 56, 56] [1, 64, 56, 56] 36,864 [3, 3] 115,605,504 | |
| │ │ └─BatchNorm2d: 3-5 [1, 64, 56, 56] [1, 64, 56, 56] 128 -- 128 | |
| │ │ └─ReLU: 3-6 [1, 64, 56, 56] [1, 64, 56, 56] -- -- -- | |
| │ └─BasicBlock: 2-2 [1, 64, 56, 56] [1, 64, 56, 56] -- -- -- | |
| │ │ └─Conv2d: 3-7 [1, 64, 56, 56] [1, 64, 56, 56] 36,864 [3, 3] 115,605,504 | |
| │ │ └─BatchNorm2d: 3-8 [1, 64, 56, 56] [1, 64, 56, 56] 128 -- 128 | |
| │ │ └─ReLU: 3-9 [1, 64, 56, 56] [1, 64, 56, 56] -- -- -- | |
| │ │ └─Conv2d: 3-10 [1, 64, 56, 56] [1, 64, 56, 56] 36,864 [3, 3] 115,605,504 | |
| │ │ └─BatchNorm2d: 3-11 [1, 64, 56, 56] [1, 64, 56, 56] 128 -- 128 | |
| │ │ └─ReLU: 3-12 [1, 64, 56, 56] [1, 64, 56, 56] -- -- -- | |
| ├─Sequential: 1-6 [1, 64, 56, 56] [1, 128, 28, 28] -- -- -- | |
| │ └─BasicBlock: 2-3 [1, 64, 56, 56] [1, 128, 28, 28] -- -- -- | |
| │ │ └─Conv2d: 3-13 [1, 64, 56, 56] [1, 128, 28, 28] 73,728 [3, 3] 57,802,752 | |
| │ │ └─BatchNorm2d: 3-14 [1, 128, 28, 28] [1, 128, 28, 28] 256 -- 256 | |
| . | |
| . | |
| . | |
| │ │ └─Conv2d: 3-49 [1, 512, 7, 7] [1, 512, 7, 7] 2,359,296 [3, 3] 115,605,504 | |
| │ │ └─BatchNorm2d: 3-50 [1, 512, 7, 7] [1, 512, 7, 7] 1,024 -- 1,024 | |
| │ │ └─ReLU: 3-51 [1, 512, 7, 7] [1, 512, 7, 7] -- -- -- | |
| ├─AdaptiveAvgPool2d: 1-9 [1, 512, 7, 7] [1, 512, 1, 1] -- -- -- | |
| ├─Linear: 1-10 [1, 512] [1, 1000] 513,000 -- 513,000 | |
| ===================================================================================================================================================================== | |
| Total params: 11,689,512 | |
| Trainable params: 11,689,512 | |
| Non-trainable params: 0 | |
| Total mult-adds (G): 1.81 | |
| ===================================================================================================================================================================== | |
| Input size (MB): 0.60 | |
| Forward/backward pass size (MB): 39.75 | |
| Params size (MB): 46.76 | |
| Estimated Total Size (MB): 87.11 | |
| ===================================================================================================================================================================== |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment