BunnyShan

Results 14 comments of BunnyShan

Evaluation results on several models are lower than reported ones.

@zhreshold Thanks, I will try it!

Evaluation results on several models are lower than reported ones.

@zhreshold I tried your config on resnet50 512 shape and got 79.5%mAP! But I can't reproduce 77.1% on resnet50 321 shape as reported in the paper, I also tried predict_module...

Evaluation results on several models are lower than reported ones.

@zhreshold I tried resnet101 that was used in the origin paper and got very poor result, need to notice that the default resnet101 layer config is different from origin paper...

Evaluation results on several models are lower than reported ones.

@zhreshold Thanks a lot! Any progress on small input size?