| Architecture | 1x1 Convolution, Batch Normalization, Convolution, Grouped Convolution, Global Average Pooling, ResNeXt Block, Residual Connection, ReLU, Max Pooling, Softmax |
|---|---|
| ID | resnext101_32x8d |
| SHOW MORE |
| Architecture | 1x1 Convolution, Batch Normalization, Convolution, Grouped Convolution, Global Average Pooling, ResNeXt Block, Residual Connection, ReLU, Max Pooling, Softmax |
|---|---|
| ID | resnext50_32x4d |
| SHOW MORE |
| Architecture | 1x1 Convolution, Batch Normalization, Convolution, Grouped Convolution, Global Average Pooling, ResNeXt Block, Residual Connection, ReLU, Max Pooling, Softmax |
|---|---|
| ID | resnext50d_32x4d |
| SHOW MORE |
| Training Techniques | SGD with Momentum, Weight Decay |
|---|---|
| Architecture | 1x1 Convolution, Batch Normalization, Convolution, Grouped Convolution, Global Average Pooling, ResNeXt Block, Residual Connection, ReLU, Max Pooling, Softmax |
| ID | tv_resnext50_32x4d |
| SHOW MORE |
A ResNeXt repeats a building block that aggregates a set of transformations with the same topology. Compared to a ResNet, it exposes a new dimension, cardinality (the size of the set of transformations) $C$, as an essential factor in addition to the dimensions of depth and width.
To load a pretrained model:
import timm
m = timm.create_model('resnext50_32x4d', pretrained=True)
m.eval()
Replace the model name with the variant you want to use, e.g. resnext50_32x4d. You can find the IDs in the model summaries at the top of this page.
You can follow the timm recipe scripts for training a new model afresh.
@article{DBLP:journals/corr/XieGDTH16,
author = {Saining Xie and
Ross B. Girshick and
Piotr Doll{\'{a}}r and
Zhuowen Tu and
Kaiming He},
title = {Aggregated Residual Transformations for Deep Neural Networks},
journal = {CoRR},
volume = {abs/1611.05431},
year = {2016},
url = {http://arxiv.org/abs/1611.05431},
archivePrefix = {arXiv},
eprint = {1611.05431},
timestamp = {Mon, 13 Aug 2018 16:45:58 +0200},
biburl = {https://dblp.org/rec/journals/corr/XieGDTH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
Image Classification on ImageNet
| MODEL | TOP 1 ACCURACY | TOP 5 ACCURACY |
|---|---|---|
| resnext50_32x4d | 79.79% | 94.61% |
| resnext50d_32x4d | 79.67% | 94.87% |
| resnext101_32x8d | 79.3% | 94.53% |
| tv_resnext50_32x4d | 77.61% | 93.68% |
