Lyz

About loss being NaN, lr_scheduler.step(), optimizer.step()

2

I've read issue #44. Like that case, I change the ResNet50 to another backbone. So I check the link you mentioned: https://discuss.pytorch.org/t/optimizer-step-before-lr-scheduler-step-error-using-gradscaler/92930/7 And therefore i change codes as below: ...

第三步打包不成功

1

FileNotFoundError: [Errno 2] No such file or directory: 'objcopy': 'objcopy' 请问这个问题怎么解决呢？

Could you plz upload the version of tensorflow and other packages? Thank you so much.

Here is my question: Does this model predict future images? Or it simply complements the frames that has lost? Waiting for your answer, and thank you so much!

Bug with txt_parser.cpp

1

``` void TXTParser::parse(const data_source& data) { docwire_log(debug)