search

xiehousen / OCGAN-Pytorch

UnOfficial PyTorch Implementation of OCGAN!
26 stars 6 forks source link

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: #1

Closed qhdjiayuan closed 4 years ago

qhdjiayuan commented 4 years ago

raceback (most recent call last): File "D:\PyCharm 2020.1\plugins\python\helpers\pydev\pydevd.py", line 1438, in _exec pydev_imports.execfile(file, globals, locals) # execute the script File "D:\PyCharm 2020.1\plugins\python\helpers\pydev_pydev_imps_pydev_execfile.py", line 18, in execfile exec(compile(contents+"\n", file, 'exec'), glob, loc) File "D:/PythonProject/OCGAN-Pytorch-master/train.py", line 523, in main() File "D:/PythonProject/OCGAN-Pytorch-master/train.py", line 191, in main Tensor,epoch, use_cuda File "D:/PythonProject/OCGAN-Pytorch-master/train.py", line 418, in train loss_ae_all.backward() File "D:\Anaconda3\lib\site-packages\torch\tensor.py", line 198, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "D:\Anaconda3\lib\site-packages\torch\autograd__init__.py", line 100, in backward allow_unreachable=True) # allow_unreachable flag

xiehousen commented 4 years ago

sorry to see it today The system we choose to reproduce the paper is the Ubuntu, I think you should choose windows; If you want to do deep learning, why not use the Ubuntu system