search

xjiangmed / LTUDA

8 stars 0 forks source link

在测试test.py时，出现unet_proto.forward() got an unexpected keyword argument 'linear_classifier'。请教一下，十分感谢 #1

Open weng-hb opened 2 months ago

weng-hb commented 2 months ago

Using Unet /content/LTUDA/code/test.py:44: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. net.load_state_dict(torch.load(args.reload_path)) Traceback (most recent call last): File "/content/LTUDA/code/test.py", line 191, in test() File "/content/LTUDA/code/test.py", line 75, in test outputs = net(data_bat, linear_classifier=False, ulp_classifier=True) File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1562, in _call_impl return forward_call(args, **kwargs) TypeError: unet_proto.forward() got an unexpected keyword argument 'linear_classifier'

weng-hb commented 2 months ago

大哥，求求了。第一次复现项目

xjiangmed commented 1 month ago

Sorry for the late reply. I forgot to update the test code. I will check and re-upload the test code as soon as possible.

weng-hb commented 1 month ago

Thank very much for you help! It is very important for my first time to replicate project. Thank you from the bottom of my's heart again.In addition, I would like to ask whether the data set used in train_CDA_PDA.py for the second training is still the same as that used in the first training?The first time model trained with your code worked is very well.Finally, wish you academic success and career success.

xjiangmed commented 1 month ago

Yes, the same data set is used for the first and second stages.

weng-hb commented 1 month ago

I am all gratitude！

LeviAov commented 2 days ago

I am all gratitude！

你好，请问你复现成功了吗？可以加个联系方式嘛，有偿