Danilo Alves Oliveira
Danilo Alves Oliveira
Hello, you can comment line 273-284 in configs/soft_teacher/base.py.
I had similar problem with loss. I received nan and the same mensage of dataset empty too. The solution for me was using bigger batch size changing **workers_per_gpu** like this...
I had similar problem. You can try use bigger batch size in **samples_per_gpu** in config file. You can try too the suggestions from #69
Hello. The train file `tools/dist_train.sh` use multiple distributed training processes by torch.distributed.launch. In this file the parameter `nproc_per_node` is the number of process per node, this number needs to be...
> @MendelXu I just set by_prob=False, and it work. But i get new error: assert len(cls_scores) == len(score_factors) AssertionError You can try this: https://github.com/microsoft/SoftTeacher/issues/83#issuecomment-955626134
> in my case, I was able to run with changing input&output node name. > > Try to change "net/%s:0" => "%s:0" 83 & 85 lines in 'tools/generate_detections.py' This solved...
> Try this: > > ``` > ffmpeg.input(stream, rtsp_transport='tcp') > ``` Thank you, this worked for me.