train.py giving index error

[ArmaanBhullar]

Hi, I was trying to run your code, Exact command being: $ CUDA_VISIBLEDEVICES=0 python train.py --lr=0.1 --seed=20170922 --decay=1e-4 Before running the command I modified train.py to make download=True in both trainset and testset. I got the following output: ==> Preparing data.. Files already downloaded and verified Files already downloaded and verified ==> Building model.. 1 Using CUDA..

Epoch: 0 Traceback (most recent call last): File "train.py", line 245, in train_loss, reg_loss, train_acc = train(epoch) File "train.py", line 165, in train trainloss += loss.data[0] IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number

Could you help as to what I'm doing wrong? I ran the debugger then, it errors out here: _File "train.py", line 165, in train trainloss += loss.data[0] IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number

[maggiezha]

this can solve the problem: https://discuss.pytorch.org/t/this-will-be-an-error-in-pytorch-0-5/19691

[dedekinds]

train_loss+=loss.data[0] ----> train_loss+=loss.item()