加载model文件夹里面的训练模型参数时出错

[Carl-Lei]

@lfz
我在测试时，加载您提供的模型'classifier_param':'./model/classifier.ckpt'时出错，错误提示是
checkpoint = torch.load('./model/classifier.ckpt')
File "C:\ProgramData\Anaconda3\lib\site-packages\torch\serialization.py", line 303, in load
return _load(f, map_location, pickle_module)
File "C:\ProgramData\Anaconda3\lib\site-packages\torch\serialization.py", line 469, in _load
result = unpickler.load()
UnicodeDecodeError: 'ascii' codec can't decode byte 0x8c in position 16: ordinal not in range(128)
请问，该怎么解决啊？谢谢！

[zhaifly]

你用的是python3？ BR. -飞跃

…

On Aug 2, 2018, at 09:26, Carl-Lei ***@***.***> wrote: @lfz 我在测试时，加载您提供的模型'classifier_param':'./model/classifier.ckpt'时出错，错误提示是 checkpoint = torch.load('./model/classifier.ckpt') File "C:\ProgramData\Anaconda3\lib\site-packages\torch\serialization.py", line 303, in load return _load(f, map_location, pickle_module) File "C:\ProgramData\Anaconda3\lib\site-packages\torch\serialization.py", line 469, in _load result = unpickler.load() UnicodeDecodeError: 'ascii' codec can't decode byte 0x8c in position 16: ordinal not in range(128) 请问，该怎么解决啊？谢谢！ — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or mute the thread.

[Carl-Lei]

@zhaifly 是的，这个要怎么解决呢

[zhaifly]

换python2 BR. -飞跃

…

On Aug 2, 2018, at 13:44, Carl-Lei ***@***.***> wrote: @zhaifly 是的，这个要怎么解决呢 — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.

[bohdanchap]

If you use a python 3 and the latest PyTorch you can read the classifier by specifying additional encoding parameter that escapes Unicode bytes:
classifier_ckpt = torch.load('model/classifier.ckpt', encoding= 'unicode_escape')

More details on this you can find on PyTorch documentation page.