Skip to content
Branch: master
Find file Copy path
Find file Copy path
2 contributors

Users who have contributed to this file

@alsrgv @tgaddair
168 lines (140 sloc) 6.35 KB
from __future__ import print_function
import argparse
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
import horovod.torch as hvd
# 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=42, metavar='S',
help='random seed (default: 42)')
parser.add_argument('--log-interval', type=int, default=10, metavar='N',
help='how many batches to wait before logging training status')
parser.add_argument('--fp16-allreduce', action='store_true', default=False,
help='use fp16 compression during allreduce')
args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()
# Horovod: initialize library.
if args.cuda:
# Horovod: pin GPU to local rank.
kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
train_dataset = \
datasets.MNIST('data-%d' % hvd.rank(), train=True, download=True,
transforms.Normalize((0.1307,), (0.3081,))
# Horovod: use DistributedSampler to partition the training data.
train_sampler =
train_dataset, num_replicas=hvd.size(), rank=hvd.rank())
train_loader =
train_dataset, batch_size=args.batch_size, sampler=train_sampler, **kwargs)
test_dataset = \
datasets.MNIST('data-%d' % hvd.rank(), train=False, transform=transforms.Compose([
transforms.Normalize((0.1307,), (0.3081,))
# Horovod: use DistributedSampler to partition the test data.
test_sampler =
test_dataset, num_replicas=hvd.size(), rank=hvd.rank())
test_loader =, batch_size=args.test_batch_size,
sampler=test_sampler, **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:
# Move model to GPU.
# Horovod: scale learning rate by the number of GPUs.
optimizer = optim.SGD(model.parameters(), * hvd.size(),
# Horovod: broadcast parameters & optimizer state.
hvd.broadcast_parameters(model.state_dict(), root_rank=0)
hvd.broadcast_optimizer_state(optimizer, root_rank=0)
# Horovod: (optional) compression algorithm.
compression = hvd.Compression.fp16 if args.fp16_allreduce else hvd.Compression.none
# Horovod: wrap optimizer with DistributedOptimizer.
optimizer = hvd.DistributedOptimizer(optimizer,
def train(epoch):
# Horovod: set epoch to sampler for shuffling.
for batch_idx, (data, target) in enumerate(train_loader):
if args.cuda:
data, target = data.cuda(), target.cuda()
output = model(data)
loss = F.nll_loss(output, target)
if batch_idx % args.log_interval == 0:
# Horovod: use train_sampler to determine the number of examples in
# this worker's partition.
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_sampler),
100. * batch_idx / len(train_loader), loss.item()))
def metric_average(val, name):
tensor = torch.tensor(val)
avg_tensor = hvd.allreduce(tensor, name=name)
return avg_tensor.item()
def test():
test_loss = 0.
test_accuracy = 0.
for data, target in test_loader:
if args.cuda:
data, target = data.cuda(), target.cuda()
output = model(data)
# sum up batch loss
test_loss += F.nll_loss(output, target, size_average=False).item()
# get the index of the max log-probability
pred =, keepdim=True)[1]
test_accuracy += pred.eq(
# Horovod: use test_sampler to determine the number of examples in
# this worker's partition.
test_loss /= len(test_sampler)
test_accuracy /= len(test_sampler)
# Horovod: average metric values across workers.
test_loss = metric_average(test_loss, 'avg_loss')
test_accuracy = metric_average(test_accuracy, 'avg_accuracy')
# Horovod: print output only on first rank.
if hvd.rank() == 0:
print('\nTest set: Average loss: {:.4f}, Accuracy: {:.2f}%\n'.format(
test_loss, 100. * test_accuracy))
for epoch in range(1, args.epochs + 1):
You can’t perform that action at this time.