main.py

'''Train CIFAR10 with PyTorch.'''
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
import torch.backends.cudnn as cudnn

import torchvision
import torchvision.transforms as transforms

import os
import argparse
import sys

from models import *
from utils import progress_bar


parser = argparse.ArgumentParser(description='PyTorch CIFAR10 Training')
parser.add_argument('--lr', default=0.01, type=float, help='learning rate')
parser.add_argument('--model', type=str, default=None, help='model name')
parser.add_argument('--batch-size', type=int, default=128, help='batch size')
parser.add_argument('--groups', type=int, default=2, help='channel groups')
parser.add_argument('--overlap', type=float, default=0.5, help='channel overlapping')
parser.add_argument('--resume', '-r', action='store_true',
                    help='resume from checkpoint')
args = parser.parse_args()

device = 'cuda:0' if torch.cuda.is_available() else 'cpu'
best_acc = 0  # best test accuracy
start_epoch = 0  # start from epoch 0 or last checkpoint epoch

# Model
assert args.model is not None
print('==> Building model..')
if args.model.startswith("VGG"):
    net = VGG(args.model, channel_groups=args.groups, overlap=args.overlap)
elif args.model.startswith("MobileNet"):
    net = MobileNet(groups=args.groups, oap=args.overlap)
elif args.model.startswith("ResNet"):
    net = eval(args.model)(groups=args.groups, oap=args.overlap)
net = net.to(device)

# Data
print('==> Preparing data..')
transform_train = 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)),
])

transform_test = transforms.Compose([
    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=True, transform=transform_train)
trainloader = torch.utils.data.DataLoader(
    trainset, batch_size=args.batch_size, shuffle=True, num_workers=2)

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

if args.resume:
    # Load checkpoint.
    print('==> Resuming from checkpoint..')
    assert os.path.isdir('checkpoint'), 'Error: no checkpoint directory found!'
    checkpoint = torch.load('./checkpoint/ckpt.pth')
    net.load_state_dict(checkpoint['net'])
    best_acc = checkpoint['acc']
    start_epoch = checkpoint['epoch']

criterion = nn.CrossEntropyLoss()

# Training
def train(epoch, optimizer):
    print('\nEpoch: %d' % epoch)
    net.train()
    train_loss = 0
    correct = 0
    total = 0
    step_time = []
    for batch_idx, (inputs, targets) in enumerate(trainloader):

        inputs, targets = inputs.to(device), targets.to(device)
        optimizer.zero_grad()
        
        outputs = net(inputs)
        loss = criterion(outputs, targets)

        loss.backward()
        optimizer.step()
        train_loss += loss.item()
        _, predicted = outputs.max(1)
        total += targets.size(0)
        correct += predicted.eq(targets).sum().item()

        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):
    global best_acc
    net.eval()
    test_loss = 0
    correct = 0
    total = 0
    with torch.no_grad():
        for batch_idx, (inputs, targets) in enumerate(testloader):
            inputs, targets = inputs.to(device), targets.to(device)
            outputs = net(inputs)
            loss = criterion(outputs, targets)

            test_loss += loss.item()
            _, predicted = outputs.max(1)
            total += targets.size(0)
            correct += predicted.eq(targets).sum().item()

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

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

    # Save checkpoint.
    acc = 100.*correct/total
    if acc > best_acc:
        print('Saving..')
        state = {
            'net': net.state_dict(),
            'acc': acc,
            'epoch': epoch,
        }
        if not os.path.isdir('checkpoint'):
            os.mkdir('checkpoint')
        torch.save(state, './checkpoint/ckpt.pth')
        best_acc = acc


for epoch in range(start_epoch, start_epoch + 350):
    if 0 <= epoch < 150:
        optimizer = optim.SGD(net.parameters(), lr=0.03,
                      momentum=0.9, weight_decay=5e-4)
    elif epoch < 250:
        optimizer = optim.SGD(net.parameters(), lr=0.003,
                      momentum=0.9, weight_decay=5e-4)
    else:
        optimizer = optim.SGD(net.parameters(), lr=0.0003,
                    momentum=0.9, weight_decay=5e-4)
    train(epoch, optimizer)  
    test(epoch)