mirror of
https://github.com/clearml/clearml
synced 2025-01-31 17:17:00 +00:00
127 lines
5.2 KiB
Python
127 lines
5.2 KiB
Python
# TRAINS - Example of pytorch with tensorboard>=v1.14
|
|
#
|
|
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
|
|
from torch.utils.tensorboard import SummaryWriter
|
|
|
|
from trains import Task
|
|
task = Task.init(project_name='examples', task_name='pytorch with tensorboard')
|
|
|
|
|
|
writer = SummaryWriter('runs')
|
|
writer.add_text('lstm', 'This is an lstm', 0)
|
|
# 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=2, 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()
|
|
|
|
torch.manual_seed(args.seed)
|
|
if args.cuda:
|
|
torch.cuda.manual_seed(args.seed)
|
|
|
|
kwargs = {'num_workers': 4, 'pin_memory': True} if args.cuda else {}
|
|
train_loader = torch.utils.data.DataLoader(datasets.MNIST('../data', train=True, download=True,
|
|
transform=transforms.Compose([
|
|
transforms.ToTensor(),
|
|
transforms.Normalize((0.1307,), (0.3081,))])),
|
|
batch_size=args.batch_size, shuffle=True, **kwargs)
|
|
test_loader = torch.utils.data.DataLoader(datasets.MNIST('../data', train=False,
|
|
transform=transforms.Compose([
|
|
transforms.ToTensor(),
|
|
transforms.Normalize((0.1307,), (0.3081,))])),
|
|
batch_size=args.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, training=self.training)
|
|
x = self.fc2(x)
|
|
return F.log_softmax(x)
|
|
|
|
|
|
model = Net()
|
|
if args.cuda:
|
|
model.cuda()
|
|
optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)
|
|
|
|
|
|
def train(epoch):
|
|
model.train()
|
|
for batch_idx, (data, target) in enumerate(train_loader):
|
|
if args.cuda:
|
|
data, target = data.cuda(), target.cuda()
|
|
data, target = Variable(data), Variable(target)
|
|
optimizer.zero_grad()
|
|
output = model(data)
|
|
loss = F.nll_loss(output, target)
|
|
loss.backward()
|
|
optimizer.step()
|
|
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), loss.data.item()))
|
|
niter = epoch*len(train_loader)+batch_idx
|
|
writer.add_scalar('Train/Loss', loss.data.item(), niter)
|
|
|
|
|
|
def test():
|
|
model.eval()
|
|
test_loss = 0
|
|
correct = 0
|
|
for niter, (data, target) in enumerate(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.item() # sum up batch loss
|
|
pred = output.data.max(1)[1] # get the index of the max log-probability
|
|
pred = pred.eq(target.data).cpu().sum()
|
|
writer.add_scalar('Test/Loss', pred, niter)
|
|
correct += pred
|
|
|
|
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):
|
|
train(epoch)
|
|
torch.save(model, '/tmp/model{}'.format(epoch))
|
|
test()
|