ID	wide_resnet101_2
LR	0.1
Epochs	90
LR Gamma	0.1
Momentum	0.9
Batch Size	32
LR Step Size	30
Weight Decay	0.0001

ID	wide_resnet50_2
LR	0.1
Epochs	90
LR Gamma	0.1
Momentum	0.9
Batch Size	32
LR Step Size	30
Weight Decay	0.0001

Wide ResNet

pytorch / vision

Last updated on Feb 12, 2021

Parameters 127 Million

FLOPs 23 Billion

File Size 242.90 MB

Training Data ImageNet

Training Resources 8x NVIDIA V100 GPUs

Training Time

Training Techniques	Weight Decay, SGD with Momentum
Architecture	1x1 Convolution, Wide Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Connection, ReLU, Max Pooling, Softmax
ID	wide_resnet101_2
LR	0.1
Epochs	90
LR Gamma	0.1
Momentum	0.9
Batch Size	32
LR Step Size	30
Weight Decay	0.0001
SHOW MORE
SHOW LESS

Parameters 69 Million

FLOPs 11 Billion

File Size 131.82 MB

Training Data ImageNet

Training Resources 8x NVIDIA V100 GPUs

Training Time

Training Techniques	Weight Decay, SGD with Momentum
Architecture	1x1 Convolution, Wide Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Connection, ReLU, Max Pooling, Softmax
ID	wide_resnet50_2
LR	0.1
Epochs	90
LR Gamma	0.1
Momentum	0.9
Batch Size	32
LR Step Size	30
Weight Decay	0.0001
SHOW MORE
SHOW LESS

README.md

Summary

Wide Residual Networks are a variant on ResNets where we decrease depth and increase the width of residual networks. This is achieved through the use of wide residual blocks.

How do I load this model?

To load a pretrained model:

import torchvision.models as models
wide_resnet50_2 = models.wide_resnet50_2(pretrained=True)

Replace the model name with the variant you want to use, e.g. wide_resnet50_2. 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>'

How do I train this model?

You can follow the torchvision recipe on GitHub for training a new model afresh.

Citation

@article{DBLP:journals/corr/ZagoruykoK16,
  author    = {Sergey Zagoruyko and
               Nikos Komodakis},
  title     = {Wide Residual Networks},
  journal   = {CoRR},
  volume    = {abs/1605.07146},
  year      = {2016},
  url       = {http://arxiv.org/abs/1605.07146},
  archivePrefix = {arXiv},
  eprint    = {1605.07146},
  timestamp = {Mon, 13 Aug 2018 16:46:42 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/ZagoruykoK16.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Results

Image Classification on ImageNet

Image Classification

BENCHMARK	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
ImageNet	Wide ResNet-101-2	Top 1 Accuracy	78.84%	# 141
		Top 5 Accuracy	94.28%	# 141
ImageNet	Wide ResNet-50-2	Top 1 Accuracy	78.51%	# 151
		Top 5 Accuracy	94.09%	# 151