main.py

'''Train CIFAR10 with PyTorch.'''
from __future__ import print_function

import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F

import torchvision
import torchvision.transforms as transforms

import numpy as np

from model import *
from utils import progress_bar, msr_init
from torch.autograd import Variable


use_cuda = torch.cuda.is_available()

# Data
print('==> Preparing data..')
transform = transforms.Compose([
    transforms.RandomCrop(32, padding=4),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=False, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=128, shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=False, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=False, num_workers=2)

classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

# Model
print('==> Building model..')
net = VGG('VGG19')
msr_init(net.features)

if use_cuda:
    net.cuda()
    net = torch.nn.DataParallel(net, device_ids=[0,1,2,3])

criterion = nn.CrossEntropyLoss()
# optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9, weight_decay=1e-4)
optimizer = optim.Adam(net.parameters(), lr=0.001, weight_decay=1e-4)

# Training
def train(epoch):
    print('Epoch: %d' % epoch)
    net.train()
    train_loss = 0
    correct = 0
    total = 0
    for batch_idx, (inputs, targets) in enumerate(trainloader):
        if use_cuda:
            inputs, targets = inputs.cuda(), targets.cuda()
        optimizer.zero_grad()
        inputs, targets = Variable(inputs), Variable(targets)
        outputs = net(inputs)
        loss = criterion(outputs, targets)
        loss.backward()
        optimizer.step()

        train_loss += loss.data[0]
        _, predicted = torch.max(outputs.data, 1)
        total += targets.size(0)
        correct += predicted.eq(targets.data).cpu().sum()

        progress_bar(batch_idx, len(trainloader), 'Loss: %.3f | Acc: %.3f%% (%d/%d)'
            % (train_loss/(batch_idx+1), 100.*correct/total, correct, total))

def test(epoch):
    net.eval()
    test_loss = 0
    correct = 0
    total = 0
    for batch_idx, (inputs, targets) in enumerate(testloader):
        if use_cuda:
            inputs, targets = inputs.cuda(), targets.cuda()
        inputs, targets = Variable(inputs, volatile=True), Variable(targets)
        outputs = net(inputs)
        loss = criterion(outputs, targets)

        test_loss += loss.data[0]
        _, predicted = torch.max(outputs.data, 1)
        total += targets.size(0)
        correct += predicted.eq(targets.data).cpu().sum()

        progress_bar(batch_idx, len(testloader), 'Loss: %.3f | Acc: %.3f%% (%d/%d)'
            % (test_loss/(batch_idx+1), 100.*correct/total, correct, total))

for epoch in range(200):
    train(epoch)
    test(epoch)