| Training Techniques | SGD with Momentum, Weight Decay |
|---|---|
| Architecture | Batch Normalization, Convolution, Global Average Pooling, Res2Net Block, ReLU |
| ID | res2net101_26w_4s |
| SHOW MORE |
| Training Techniques | SGD with Momentum, Weight Decay |
|---|---|
| Architecture | Batch Normalization, Convolution, Global Average Pooling, Res2Net Block, ReLU |
| ID | res2net50_14w_8s |
| SHOW MORE |
| Training Techniques | SGD with Momentum, Weight Decay |
|---|---|
| Architecture | Batch Normalization, Convolution, Global Average Pooling, Res2Net Block, ReLU |
| ID | res2net50_26w_4s |
| SHOW MORE |
| Training Techniques | SGD with Momentum, Weight Decay |
|---|---|
| Architecture | Batch Normalization, Convolution, Global Average Pooling, Res2Net Block, ReLU |
| ID | res2net50_26w_6s |
| SHOW MORE |
| Training Techniques | SGD with Momentum, Weight Decay |
|---|---|
| Architecture | Batch Normalization, Convolution, Global Average Pooling, Res2Net Block, ReLU |
| ID | res2net50_26w_8s |
| SHOW MORE |
| Training Techniques | SGD with Momentum, Weight Decay |
|---|---|
| Architecture | Batch Normalization, Convolution, Global Average Pooling, Res2Net Block, ReLU |
| ID | res2net50_48w_2s |
| SHOW MORE |
Res2Net is an image model that employs a variation on bottleneck residual blocks, Res2Net Blocks. The motivation is to be able to represent features at multiple scales. This is achieved through a novel building block for CNNs that constructs hierarchical residual-like connections within one single residual block. This represents multi-scale features at a granular level and increases the range of receptive fields for each network layer.
To load a pretrained model:
import timm
m = timm.create_model('res2net50_14w_8s', pretrained=True)
m.eval()
Replace the model name with the variant you want to use, e.g. res2net50_14w_8s. 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{Gao_2021,
title={Res2Net: A New Multi-Scale Backbone Architecture},
volume={43},
ISSN={1939-3539},
url={http://dx.doi.org/10.1109/TPAMI.2019.2938758},
DOI={10.1109/tpami.2019.2938758},
number={2},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
publisher={Institute of Electrical and Electronics Engineers (IEEE)},
author={Gao, Shang-Hua and Cheng, Ming-Ming and Zhao, Kai and Zhang, Xin-Yu and Yang, Ming-Hsuan and Torr, Philip},
year={2021},
month={Feb},
pages={652–662}
}
Image Classification on ImageNet
| MODEL | TOP 1 ACCURACY | TOP 5 ACCURACY |
|---|---|---|
| res2net50_26w_8s | 79.19% | 94.37% |
| res2net101_26w_4s | 79.19% | 94.43% |
| res2net50_26w_6s | 78.57% | 94.12% |
| res2net50_14w_8s | 78.14% | 93.86% |
| res2net50_26w_4s | 77.99% | 93.85% |
| res2net50_48w_2s | 77.53% | 93.56% |
