soeaver / AirNet-PyTorch

Implementation of the paper ''Attention Inspiring Receptive-fields Network''

AirNet-PyTorch

Implementation of the paper ''Attention Inspiring Receptive-fields Network'' (under review), which contains the evaluation code and trained models. By:

Lu Yang, Qing Song, Yingqi Wu and Mengjie Hu

Install

• Install PyTorch>=0.3.0
• Install torchvision>=0.2.0
• Clone

  git clone https://github.com/soeaver/AirNet-PyTorch
  

Evaluation

• Download the trained models, and move them to the ckpts folder.
• Run the eval.py:

  python eval.py --gpu_id 0 --arch airnet50_1x64d --model_weights ./ckpts/air50_1x64d.pth
  

• The results will be consistent with the paper.

Results

ImageNet1k

Single-crop (224x224) validation error rate is reported.

Network	Flops (G)	Params (M)	Top-1 Error (%)	Top-5 Error (%)	Download
AirNet50-1x64d (r=16)	4.36	25.7	22.11	6.18	GoogleDrive
AirNet50-1x64d (r=2)	4.72	27.4	21.83	5.89	GoogleDrive
AirNeXt50-32x4d	5.29	25.5	20.87	5.52	GoogleDrive

Other Resources (from DPNs)

ImageNet-1k Trainig/Validation List:

• Download link: GoogleDrive

ImageNet-1k category name mapping table:

• Download link: GoogleDrive