Autumn Z

optimizers shoould be used for params from different Module

1

So in your example, Automaticweightedloss is a unique module of Model, another optimzer should be used to update the params separately, or the params would follow the direction of model...

CrossEntropyLoss reduction write error

1

should `loss = (- targets * log_probs).mean(0).sum()` in [https://github.com/michuanhaohao/reid-strong-baseline/blob/master/layers/triplet_loss.py#L146](url) be supposed to `loss = (- targets * log_probs).sum(1).mean()`?

ort_session->Run报段错误

2

请问onnxruntime版本是多少呢，ort_session->Run段错误是否也跟官方导出onnx与代码中使用的不一致有关呢，谢谢