mxcheeto

Abonormal loss tendency when traning in smaller batch size

1

When reproducing the experiment under maptr_tiny_r50_24e.py using 2 batches (per GPU) x 4 GPUs (2080 Ti), the obtained loss results seem abnormal, especially the loss_dir group:   However, the...

When I reproduced the program file in vectormapnet.py, I found that the result fluctuated to a certain extent during multiple training with the same configuration. Up to 0.8 mAP (evaluated...