徐锐

非常感谢你分享的代码！我用你的代码跑了一下实验，有些文件不是unix编码风格，需要使用set ff=unix命令转换。你建议使用python3来运行代码，但是text2token.py是python2风格，导致之后data2json.sh的输出json文件是空。请问该如何修改代码？感谢

just train person

1

how should i do if just train and test person?i wanna to train a person detector.thks

dont make sense of TransformParamsLayer

1

hi ,i have read TransformParamsLayer.py again and again,still cannot make sense what TransformParamsLayer doing.could you explain it ? thank you very much. and my email is [email protected].

how train on my own dataset?

5

thanks for sharing code. i wonder if i can train on my own dataset, and how should i prepare the pkl file?

about the object detector FPN code

1

thanks for sharing code. i am very interested in your code,could you release the object detector FPN code? thank you

trainning error

1

sorry to disturb u, when i using the train_VGG19.py to train the net,when epoch reach 6,there are out of memory error. the error is portrayed as below: RuntimeError: cuda runtime...

evaluate the network while i code the python evaluation.py

关于annotation问题

1

你好，我下载的mpii数据集的annotation是mat文件，而不是josn文件，你能不能把json文件annotation发一下，谢谢。[email protected]