Please Help me to solve this Error

1

Hello there,
I tried to solve this now for 2 Hours and I still don’t know, what I should change in my code. :frowning:
Can You please help me?

Here’s my Code:

import os
import torch
import torch.nn as nn
import torch.nn.functional as f
from torch.autograd import Variable
import torch.optim as optim


class MeinNetz(nn.Module):
    def __init__(self):
        super(MeinNetz, self).__init__()
        self.lin1 = nn.Linear(10, 10)
        self.lin2 = nn.Linear(10, 10)

    def forward(self, x):
        x = f.relu(self.lin1(x))
        x = self.lin2(x)
        return x

    def num_flat_features(self, x):
        size = x.size()[1:]
        num = 1
        for i in size:
            num *= i
        return num


#netz = MeinNetz()

if os.path.isfile('MeinNetz.pt'):
    netz = torch.load('MeinNetz.pt')

for i in range(1000):
    x = [1, 0, 0, 0, 1, 0, 0, 0, 1, 1]
    input = Variable(torch.Tensor([x for _ in range(10)]))

    out = netz(input)

    x = [0, 1, 1, 1, 0, 1, 1, 1, 0, 0]
    target = Variable(torch.Tensor([x for _ in range(10)]))
    criterion = nn.MSELoss()
    loss = criterion(out, target)
    print(loss)

    netz.zero_grad()
    loss.backward()
    optimizer = optim.SGD(netz.parameters(), lr=0.10)
    optimizer.step()

torch.save(netz, 'MeinNetz.pt')

And this is the Error:

/Users/***/PycharmProjects/Pytorch/venv/mnist.py:40: UserWarning: Implicit dimension choice for log_softmax has been deprecated. Change the call to include dim=X as an argument.
  return F.log_softmax(x)
Traceback (most recent call last):
  File "/Users/***/PycharmProjects/Pytorch/venv/mnist.py", line 63, in <module>
    train(epoch)
  File "/Users/***/PycharmProjects/Pytorch/venv/mnist.py", line 59, in train
    loss.data[0]))
IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number

Thank You

2

what is your file name? the one you posted

3

your code runs fine with me there is no error. i think you are executing another file, can you look into that?
the output of your code is:

tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
tensor(3.1766e-15, grad_fn=<MseLossBackward>)
4

My File is named: mnist.py

5

Oh, yes I posted the wrong code, sorry!

Here is the real code:

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.autograd import Variable

kwargs = {}
train_data = torch.utils.data.DataLoader(datasets.MNIST('data',train=True, download=True,
                                                        transform=transforms.Compose([transforms.ToTensor(),
                                                                                      transforms.Normalize((0.1307,),
                                                                                                           (0.3081,))])),
                                         batch_size=64, shuffle=True, **kwargs)
test_data = torch.utils.data.DataLoader(datasets.MNIST('data', train=False,
                                                       transform=transforms.Compose([transforms.ToTensor(),
                                                                                     transforms.Normalize((0.1307,),
                                                                                                          (0.3081,))])),
                                        batch_size=64, shuffle=True, **kwargs)

class Netz(nn.Module):
    def __init__(self):
        super(Netz, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv_dropout = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 60)
        self.fc2 = nn.Linear(60, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = F.max_pool2d(x, 2)
        x = F.relu(x)
        x = self.conv2(x)
        x = self.conv_dropout(x)
        x = F.max_pool2d(x, 2)
        x = F.relu(x)
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return F.log_softmax(x)

model = Netz()

optimizer = optim.SGD(model.parameters(), lr=0.1, momentum=0.8)
def train(epoch):
    model.train()
    for batch_id, (data, target) in enumerate(train_data):
        data = Variable(data)
        target = Variable(target)
        optimizer.zero_grad()
        out = model(data)
        criterion = F.nll_loss
        loss = criterion(out, target)
        loss.backward()
        optimizer.step()
        print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(epoch, batch_id * len(data),
                                                                       len(train_data.dataset),
                                                                       100. * batch_id / len(train_data),
                                                                       loss.data[0]))


for epoch in range(1, 30):
    train(epoch)

Sorry for my dumbness

6

I think you must put loss.item() instead of loss.data[0] in your print statement

1 Like
7

Actually I don’t get any errors when executing the above code. What is you pytorch version?

8

I use Pytorch 1.0 on MacOS with python 3.7 and without CUDA

9

Now I changed loss.data[0] in the print statement to loss.item() and now it works.

Thank you very much, ErikJ

Regards
DerBerliner

10

Could You just undo Your changes in Your Post?
Thank You

Regards
DerBerliner

11

Ah ok I am using 0.4.1 so I guess it got deprecated in 1.0 . No problem :slight_smile: