songwsx/person_search_demo

使用自己的reid模型,测试报错

Opened this issue · 2 comments

作者您好,我使用自己在 reid-strong-baseline 训练得到的模型,运行search.py时报错,报错信息:
Traceback (most recent call last):

File "E:\person_search_demo\search.py", line 228, in
output=opt.output)

File "E:\person_search_demo\search.py", line 38, in detect
reidModel.load_param(reidCfg.TEST.WEIGHT)

File "E:\person_search_demo\reid\modeling\baseline.py", line 63, in load_param
param_dict = torch.load(trained_path)

File "d:\anaconda3\envs\torch\lib\site-packages\torch\serialization.py", line 387, in load
return _load(f, map_location, pickle_module, **pickle_load_args)

File "d:\anaconda3\envs\torch\lib\site-packages\torch\serialization.py", line 574, in _load
result = unpickler.load()

ModuleNotFoundError: No module named 'modeling'
请问可以提供一些解决的建议吗?

sgg22 commented

同样的问题

一样,请问解决了嘛