导入您提供的预训练模型时报错

hyhzzzz commented 4 years ago

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "main.py", line 163, in main() File "main.py", line 144, in main load_pretrained_weights(model, args.load_weights) File "/home/hyhzzzz/デスクトップ/PVPM-master/torchreid/utils/torchtools.py", line 281, in load_pretrained_weights checkpoint = load_checkpoint(weight_path) File "/home/hyhzzzz/デスクトップ/PVPM-master/torchreid/utils/torchtools.py", line 89, in load_checkpoint checkpoint = torch.load(fpath, map_location=map_location,pickle_module=pickle, ) File "/home/hyhzzzz/anaconda3/lib/python3.7/site-packages/torch/serialization.py", line 593, in load return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) File "/home/hyhzzzz/anaconda3/lib/python3.7/site-packages/torch/serialization.py", line 773, in _legacy_load result = unpickler.load() UnicodeDecodeError: 'utf-8' codec can't decode byte 0xda in position 1: invalid continuation byte

推测是由于我的环境是python3导致但阅读代码似乎已对python3读取模型作了兼容但仍然出现了问题

hyhzzzz commented 4 years ago

我查了一些资料关于这个兼容问题其给的解决方案和代码中的兼容写法几乎一模一样但似乎并不起作用

hh23333 commented 4 years ago

参考issue#11 ，可能是因为模型的问题，如果使用python3,建议重新训一下，不要使用我提供的模型

hh23333 / PVPM

导入您提供的预训练模型时报错 #9