Res2Net Keras - Converted from original pytorch model

The official pytorch implemention of the paper "Res2Net: A New Multi-scale Backbone Architecture"

Our paper is accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

Introduction

We propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the range of receptive fields for each network layer. The proposed Res2Net block can be plugged into the state-of-the-art backbone CNN models, e.g. , ResNet, ResNeXt, BigLittleNet, and DLA. We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models.

Res2Net module

Useage

Requirement

PyTorch>=0.4.1 (PyTorch1.0 and 1.1 are supported.)

Examples

git clone https://github.com/gasvn/Res2Net.git

from res2net import res2net50
model = res2net50(pretrained=True)

Input image should be normalized as follows:

normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                  std=[0.229, 0.224, 0.225])

(By default, the model will be downloaded automatically. If the default download link is not available, please refer to the Download Link listed on Pretrained models.)

Pretrained models

model	#Params	GFLOPs	top-1 error	top-5 error	Link
Res2Net-50-48w-2s	25.29M	4.2	22.68	6.47	OneDrive
Res2Net-50-26w-4s	25.70M	4.2	22.01	6.15	OneDrive
Res2Net-50-14w-8s	25.06M	4.2	21.86	6.14	OneDrive
Res2Net-50-26w-6s	37.05M	6.3	21.42	5.87	OneDrive
Res2Net-50-26w-8s	48.40M	8.3	20.80	5.63	OneDrive
Res2Net-101-26w-4s	45.21M	8.1	20.81	5.57	OneDrive
Res2NeXt-50	24.67M	4.2	21.76	6.09	OneDrive
Res2Net-DLA-60	21.15M	4.2	21.53	5.80	OneDrive
Res2NeXt-DLA-60	17.33M	3.6	21.55	5.86	OneDrive

The download link from Baidu Disk is now available. (Baidu Disk password: vbix)

Applications

Pose Estimation
Salient object detection
Instance segmentation
Object detection
Segmantic segmentation (Coming soon)
More applications will be released soon

Citation

If you find this work or code is helpful in your research, please cite:

@article{gao2019res2net,
  title={Res2Net: A New Multi-scale Backbone Architecture},
  author={Gao, Shang-Hua and Cheng, Ming-Ming and Zhao, Kai and Zhang, Xin-Yu and Yang, Ming-Hsuan and Torr, Philip},
  journal={IEEE TPAMI},
  year={2020},
  doi={10.1109/TPAMI.2019.2938758}, 
}

Contact

If you have any questions, feel free to E-mail me via: shgao(at)live.com

evitself/Res2Net