You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
308 lines
7.8 KiB
308 lines
7.8 KiB
# Summary
|
|
|
|
**Residual Networks**, or **ResNets**, learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. Instead of hoping each few stacked layers directly fit a desired underlying mapping, residual nets let these layers fit a residual mapping. They stack [residual blocks](https://paperswithcode.com/method/residual-block) ontop of each other to form network: e.g. a ResNet-50 has fifty layers using these blocks.
|
|
|
|
{% include 'code_snippets.md' %}
|
|
|
|
## How do I train this model?
|
|
|
|
You can follow the [timm recipe scripts](https://rwightman.github.io/pytorch-image-models/scripts/) for training a new model afresh.
|
|
|
|
## Citation
|
|
|
|
```BibTeX
|
|
@article{DBLP:journals/corr/HeZRS15,
|
|
author = {Kaiming He and
|
|
Xiangyu Zhang and
|
|
Shaoqing Ren and
|
|
Jian Sun},
|
|
title = {Deep Residual Learning for Image Recognition},
|
|
journal = {CoRR},
|
|
volume = {abs/1512.03385},
|
|
year = {2015},
|
|
url = {http://arxiv.org/abs/1512.03385},
|
|
archivePrefix = {arXiv},
|
|
eprint = {1512.03385},
|
|
timestamp = {Wed, 17 Apr 2019 17:23:45 +0200},
|
|
biburl = {https://dblp.org/rec/journals/corr/HeZRS15.bib},
|
|
bibsource = {dblp computer science bibliography, https://dblp.org}
|
|
}
|
|
```
|
|
|
|
<!--
|
|
Models:
|
|
- Name: resnet26
|
|
Metadata:
|
|
FLOPs: 3026804736
|
|
Training Data:
|
|
- ImageNet
|
|
Architecture:
|
|
- 1x1 Convolution
|
|
- Batch Normalization
|
|
- Bottleneck Residual Block
|
|
- Convolution
|
|
- Global Average Pooling
|
|
- Max Pooling
|
|
- ReLU
|
|
- Residual Block
|
|
- Residual Connection
|
|
- Softmax
|
|
File Size: 64129972
|
|
Tasks:
|
|
- Image Classification
|
|
ID: resnet26
|
|
Crop Pct: '0.875'
|
|
Image Size: '224'
|
|
Interpolation: bicubic
|
|
Code: https://github.com/rwightman/pytorch-image-models/blob/d8e69206be253892b2956341fea09fdebfaae4e3/timm/models/resnet.py#L675
|
|
In Collection: ResNet
|
|
- Name: tv_resnet152
|
|
Metadata:
|
|
FLOPs: 14857660416
|
|
Epochs: 90
|
|
Batch Size: 32
|
|
Training Data:
|
|
- ImageNet
|
|
Training Techniques:
|
|
- SGD with Momentum
|
|
- Weight Decay
|
|
Architecture:
|
|
- 1x1 Convolution
|
|
- Batch Normalization
|
|
- Bottleneck Residual Block
|
|
- Convolution
|
|
- Global Average Pooling
|
|
- Max Pooling
|
|
- ReLU
|
|
- Residual Block
|
|
- Residual Connection
|
|
- Softmax
|
|
File Size: 241530880
|
|
Tasks:
|
|
- Image Classification
|
|
ID: tv_resnet152
|
|
LR: 0.1
|
|
Crop Pct: '0.875'
|
|
LR Gamma: 0.1
|
|
Momentum: 0.9
|
|
Image Size: '224'
|
|
LR Step Size: 30
|
|
Weight Decay: 0.0001
|
|
Interpolation: bilinear
|
|
Code: https://github.com/rwightman/pytorch-image-models/blob/9a25fdf3ad0414b4d66da443fe60ae0aa14edc84/timm/models/resnet.py#L769
|
|
In Collection: ResNet
|
|
- Name: resnet18
|
|
Metadata:
|
|
FLOPs: 2337073152
|
|
Training Data:
|
|
- ImageNet
|
|
Architecture:
|
|
- 1x1 Convolution
|
|
- Batch Normalization
|
|
- Bottleneck Residual Block
|
|
- Convolution
|
|
- Global Average Pooling
|
|
- Max Pooling
|
|
- ReLU
|
|
- Residual Block
|
|
- Residual Connection
|
|
- Softmax
|
|
File Size: 46827520
|
|
Tasks:
|
|
- Image Classification
|
|
ID: resnet18
|
|
Crop Pct: '0.875'
|
|
Image Size: '224'
|
|
Interpolation: bilinear
|
|
Code: https://github.com/rwightman/pytorch-image-models/blob/d8e69206be253892b2956341fea09fdebfaae4e3/timm/models/resnet.py#L641
|
|
In Collection: ResNet
|
|
- Name: resnet50
|
|
Metadata:
|
|
FLOPs: 5282531328
|
|
Training Data:
|
|
- ImageNet
|
|
Architecture:
|
|
- 1x1 Convolution
|
|
- Batch Normalization
|
|
- Bottleneck Residual Block
|
|
- Convolution
|
|
- Global Average Pooling
|
|
- Max Pooling
|
|
- ReLU
|
|
- Residual Block
|
|
- Residual Connection
|
|
- Softmax
|
|
File Size: 102488165
|
|
Tasks:
|
|
- Image Classification
|
|
ID: resnet50
|
|
Crop Pct: '0.875'
|
|
Image Size: '224'
|
|
Interpolation: bicubic
|
|
Code: https://github.com/rwightman/pytorch-image-models/blob/d8e69206be253892b2956341fea09fdebfaae4e3/timm/models/resnet.py#L691
|
|
In Collection: ResNet
|
|
- Name: resnet34
|
|
Metadata:
|
|
FLOPs: 4718469120
|
|
Training Data:
|
|
- ImageNet
|
|
Architecture:
|
|
- 1x1 Convolution
|
|
- Batch Normalization
|
|
- Bottleneck Residual Block
|
|
- Convolution
|
|
- Global Average Pooling
|
|
- Max Pooling
|
|
- ReLU
|
|
- Residual Block
|
|
- Residual Connection
|
|
- Softmax
|
|
File Size: 87290831
|
|
Tasks:
|
|
- Image Classification
|
|
ID: resnet34
|
|
Crop Pct: '0.875'
|
|
Image Size: '224'
|
|
Interpolation: bilinear
|
|
Code: https://github.com/rwightman/pytorch-image-models/blob/d8e69206be253892b2956341fea09fdebfaae4e3/timm/models/resnet.py#L658
|
|
In Collection: ResNet
|
|
- Name: resnetblur50
|
|
Metadata:
|
|
FLOPs: 6621606912
|
|
Training Data:
|
|
- ImageNet
|
|
Architecture:
|
|
- 1x1 Convolution
|
|
- Batch Normalization
|
|
- Blur Pooling
|
|
- Bottleneck Residual Block
|
|
- Convolution
|
|
- Global Average Pooling
|
|
- Max Pooling
|
|
- ReLU
|
|
- Residual Block
|
|
- Residual Connection
|
|
- Softmax
|
|
File Size: 102488165
|
|
Tasks:
|
|
- Image Classification
|
|
ID: resnetblur50
|
|
Crop Pct: '0.875'
|
|
Image Size: '224'
|
|
Interpolation: bicubic
|
|
Code: https://github.com/rwightman/pytorch-image-models/blob/d8e69206be253892b2956341fea09fdebfaae4e3/timm/models/resnet.py#L1160
|
|
In Collection: ResNet
|
|
- Name: tv_resnet34
|
|
Metadata:
|
|
FLOPs: 4718469120
|
|
Epochs: 90
|
|
Batch Size: 32
|
|
Training Data:
|
|
- ImageNet
|
|
Training Techniques:
|
|
- SGD with Momentum
|
|
- Weight Decay
|
|
Architecture:
|
|
- 1x1 Convolution
|
|
- Batch Normalization
|
|
- Bottleneck Residual Block
|
|
- Convolution
|
|
- Global Average Pooling
|
|
- Max Pooling
|
|
- ReLU
|
|
- Residual Block
|
|
- Residual Connection
|
|
- Softmax
|
|
File Size: 87306240
|
|
Tasks:
|
|
- Image Classification
|
|
ID: tv_resnet34
|
|
LR: 0.1
|
|
Crop Pct: '0.875'
|
|
LR Gamma: 0.1
|
|
Momentum: 0.9
|
|
Image Size: '224'
|
|
LR Step Size: 30
|
|
Weight Decay: 0.0001
|
|
Interpolation: bilinear
|
|
Code: https://github.com/rwightman/pytorch-image-models/blob/9a25fdf3ad0414b4d66da443fe60ae0aa14edc84/timm/models/resnet.py#L745
|
|
In Collection: ResNet
|
|
- Name: tv_resnet101
|
|
Metadata:
|
|
FLOPs: 10068547584
|
|
Epochs: 90
|
|
Batch Size: 32
|
|
Training Data:
|
|
- ImageNet
|
|
Training Techniques:
|
|
- SGD with Momentum
|
|
- Weight Decay
|
|
Architecture:
|
|
- 1x1 Convolution
|
|
- Batch Normalization
|
|
- Bottleneck Residual Block
|
|
- Convolution
|
|
- Global Average Pooling
|
|
- Max Pooling
|
|
- ReLU
|
|
- Residual Block
|
|
- Residual Connection
|
|
- Softmax
|
|
File Size: 178728960
|
|
Tasks:
|
|
- Image Classification
|
|
ID: tv_resnet101
|
|
LR: 0.1
|
|
Crop Pct: '0.875'
|
|
LR Gamma: 0.1
|
|
Momentum: 0.9
|
|
Image Size: '224'
|
|
LR Step Size: 30
|
|
Weight Decay: 0.0001
|
|
Interpolation: bilinear
|
|
Code: https://github.com/rwightman/pytorch-image-models/blob/9a25fdf3ad0414b4d66da443fe60ae0aa14edc84/timm/models/resnet.py#L761
|
|
In Collection: ResNet
|
|
- Name: tv_resnet50
|
|
Metadata:
|
|
FLOPs: 5282531328
|
|
Epochs: 90
|
|
Batch Size: 32
|
|
Training Data:
|
|
- ImageNet
|
|
Training Techniques:
|
|
- SGD with Momentum
|
|
- Weight Decay
|
|
Architecture:
|
|
- 1x1 Convolution
|
|
- Batch Normalization
|
|
- Bottleneck Residual Block
|
|
- Convolution
|
|
- Global Average Pooling
|
|
- Max Pooling
|
|
- ReLU
|
|
- Residual Block
|
|
- Residual Connection
|
|
- Softmax
|
|
File Size: 102502400
|
|
Tasks:
|
|
- Image Classification
|
|
ID: tv_resnet50
|
|
LR: 0.1
|
|
Crop Pct: '0.875'
|
|
LR Gamma: 0.1
|
|
Momentum: 0.9
|
|
Image Size: '224'
|
|
LR Step Size: 30
|
|
Weight Decay: 0.0001
|
|
Interpolation: bilinear
|
|
Code: https://github.com/rwightman/pytorch-image-models/blob/9a25fdf3ad0414b4d66da443fe60ae0aa14edc84/timm/models/resnet.py#L753
|
|
In Collection: ResNet
|
|
Collections:
|
|
- Name: ResNet
|
|
Paper:
|
|
title: Deep Residual Learning for Image Recognition
|
|
url: https://papperswithcode.com//paper/deep-residual-learning-for-image-recognition
|
|
type: model-index
|
|
Type: model-index
|
|
-->
|