zhang qiang

Thank you for your reply. In my application, the input size is 512x512. I am using mmdetection to train my dataset and want to test the performace of FreeAnchor. I...

@zhangxiaosong18 I change the config file like (MIN_SIZE=600, MAX_SIZE=833), and still got error. 2020-01-19 05:29:33,311 maskrcnn_benchmark.trainer INFO: eta: 1:48:16 iter: 319500 loss: 1.6501 (2.0420) loss_retina_positive: 1.4884 (1.8823) loss_retina_negative: 0.1492 (0.1597)...

@zhangxiaosong18 anything update ？

Hi @mathmanu I think it's hard to reproduce the original mAP because the network(jdetnet21v2) is so small. I only get 69% mAP(initial), and the original mAP is 79.8%. Could you...