ykotseruba
commented
2 years ago Hi, I don't think it's a docker issue, it could be due to Windows. I haven't tested the code on Windows, but I was able to reproduce the results when training the model in docker on multiple Linux machines. There could also be some fluctuations in the results due to random initialization, perhaps you can try training it several times.
Hi， After I retrained PCPA with the settings in the paper, the performance was not as good as the data in the paper. While you were answering your other question, I noticed that the performance on JAAD would drop due to some issues, but it was still higher than my results. I use the windows system to train and do not use docker. I want to know if this is the main reason and whether using docker will affect the experimental results. Thanks for your answer.