PyTorch Environment

This article installs PyTorch as an reusable environment.

Reusing the Environment

If you want to reuse this environment in another article you have to:

  • Create a new article
  • Insert a python cell
  • Activate the runtime settings in the runtime panel on the far right
  • Bring up the environments dropdown
  • Select the Transclude environment… option
  • Search for this article mk/pytorch by entering pytorch into the search field
  • Select this article and the Pytorch environment in it


conda install -q -y pytorch torchvision -c soumith

MNIST Sample

This is running the MNIST sample.

from __future__ import print_function
import argparse
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

# Training settings
parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
parser.add_argument('--batch-size', type=int, default=64, metavar='N',
                    help='input batch size for training (default: 64)')
parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',
                    help='input batch size for testing (default: 1000)')
parser.add_argument('--epochs', type=int, default=10, metavar='N',
                    help='number of epochs to train (default: 10)')
parser.add_argument('--lr', type=float, default=0.01, metavar='LR',
                    help='learning rate (default: 0.01)')
parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
                    help='SGD momentum (default: 0.5)')
parser.add_argument('--no-cuda', action='store_true', default=False,
                    help='disables CUDA training')
parser.add_argument('--seed', type=int, default=1, metavar='S',
                    help='random seed (default: 1)')
parser.add_argument('--log-interval', type=int, default=10, metavar='N',
                    help='how many batches to wait before logging training status')
args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()

if args.cuda:

kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
train_loader =
    datasets.MNIST('/files/', train=True, download=True,
                       transforms.Normalize((0.1307,), (0.3081,))
    batch_size=args.batch_size, shuffle=True, **kwargs)
test_loader =
    datasets.MNIST('/files/', train=False, transform=transforms.Compose([
                       transforms.Normalize((0.1307,), (0.3081,))
    batch_size=args.test_batch_size, shuffle=True, **kwargs)

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = F.dropout(x,
        x = self.fc2(x)
        return F.log_softmax(x)

model = Net()
if args.cuda:

optimizer = optim.SGD(model.parameters(),, momentum=args.momentum)

def train(epoch):
    for batch_idx, (data, target) in enumerate(train_loader):
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data), Variable(target)
        output = model(data)
        loss = F.nll_loss(output, target)
        if batch_idx % args.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),[0]))

def test():
    test_loss = 0
    correct = 0
    for data, target in test_loader:
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        test_loss += F.nll_loss(output, target, size_average=False).data[0] # sum up batch loss
        pred =, keepdim=True)[1] # get the index of the max log-probability
        correct += pred.eq(

    test_loss /= len(test_loader.dataset)
    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))

for epoch in range(1, args.epochs + 1):

© 2018 Nextjournal GmbH