| Training Techniques | Weight Decay, SGD with Momentum |
|---|---|
| Architecture | 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax |
| ID | resnet101 |
| SHOW MORE |
| Training Techniques | Weight Decay, SGD with Momentum |
|---|---|
| Architecture | 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax |
| ID | resnet152 |
| SHOW MORE |
| Training Techniques | Weight Decay, SGD with Momentum |
|---|---|
| Architecture | 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax |
| ID | resnet18 |
| SHOW MORE |
| Training Techniques | Weight Decay, SGD with Momentum |
|---|---|
| Architecture | 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax |
| ID | resnet34 |
| SHOW MORE |
| Training Techniques | Weight Decay, SGD with Momentum |
|---|---|
| Architecture | 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax |
| ID | resnet50 |
| SHOW MORE |
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 ontop of each other to form network: e.g. a ResNet-50 has fifty layers using these blocks.
To load a pretrained model:
import torchvision.models as models
resnet18 = models.resnet18(pretrained=True)
Replace the model name with the variant you want to use, e.g. resnet18. You can find
the IDs in the model summaries at the top of this page.
To evaluate the model, use the image classification recipes from the library.
python train.py --test-only --model='<model_name>'
You can follow the torchvision recipe on GitHub for training a new model afresh.
@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}
}
Image Classification on ImageNet
| MODEL | TOP 1 ACCURACY | TOP 5 ACCURACY |
|---|---|---|
| ResNet-152 | 78.31% | 94.06% |
| ResNet-101 | 77.37% | 93.56% |
| ResNet-50 | 76.15% | 92.87% |
| ResNet-34 | 73.3% | 91.42% |
| ResNet-18 | 69.76% | 89.08% |
