Hi. Thanks for sharing your brilliant work. But I have trouble running inpainting code. I'm using python 2, pytorch 0.3.0. The error message is listed as following. I guess something happens near the end of the training, but I have no idea. I would appreciate it if anyone can tell me how to fix it.
ValueError Traceback (most recent call last)
<ipython-input-9-ac0684da7936> in <module>()
23
24 p = get_params(OPT_OVER, net, net_input)
---> 25 optimize(OPTIMIZER, p, closure, LR, num_iter)
/home/atlantix/deep-image-prior/utils/common_utils.pyc in optimize(optimizer_type, parameters, closure, LR, num_iter)
233 for j in range(num_iter):
234 optimizer.zero_grad()
--> 235 closure()
236 optimizer.step()
237 else:
<ipython-input-9-ac0684da7936> in closure()
13 total_loss.backward()
14
---> 15 print ('Iteration %05d Loss %f' % (i, total_loss.data[0]), '\r', end='')
16 if PLOT and i % show_every == 0:
17 out_np = var_to_np(out)
/usr/local/lib/python2.7/dist-packages/ipykernel/iostream.pyc in write(self, string)
315
316 is_child = (not self._is_master_process())
--> 317 self._buffer.write(string)
318 if is_child:
319 # newlines imply flush in subprocesses
ValueError: I/O operation on closed file
Hi. Thanks for sharing your brilliant work. But I have trouble running inpainting code. I'm using python 2, pytorch 0.3.0. The error message is listed as following. I guess something happens near the end of the training, but I have no idea. I would appreciate it if anyone can tell me how to fix it.