I am having trouble with saving my network on PyTorch.
I have the following code here: It is from this site https://nextjournal.com/gkoehler/pytorch-mnist#training-the-model
def train(epoch):
network.train()
for batch_idx, (data, target) in enumerate(train_loader):
optimizer.zero_grad()
output = network(data)
loss = F.nll_loss(output, target)
loss.backward()
optimizer.step()
if batch_idx % log_interval == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()))
train_losses.append(loss.item())
train_counter.append(
(batch_idx*64) + ((epoch-1)*len(train_loader.dataset)))
torch.save(network.state_dict(), '/results/model.pth')
torch.save(optimizer.state_dict(), '/results/optimizer.pth')
However I am having trouble when I run my model, it doesn't want to save. This is the error I get:
Traceback (most recent call last):
File "<ipython-input-23-901bbf4e7eff>", line 54, in <module>
train(epoch)
File "<ipython-input-23-901bbf4e7eff>", line 16, in train
torch.save(network.state_dict(), '\results\model.pth')
File "C:\Users\User\anaconda3\lib\site-packages\torch\serialization.py", line 628, in save
with _open_zipfile_writer(f) as opened_zipfile:
File "C:\Users\User\anaconda3\lib\site-packages\torch\serialization.py", line 502, in
_open_zipfile_writer
return container(name_or_buffer)
File "C:\Users\User\anaconda3\lib\site-packages\torch\serialization.py", line 473, in
__init__
super().__init__(torch._C.PyTorchFileWriter(self.name))
RuntimeError: Parent directory \results does not exist.
Where does torch.save save to on a windows PC? I don't think I have the filename that the tutorial on the website was using?