original_train.py

# https://github.com/pytorch/vision/blob/master/torchvision/models/__init__.py
import argparse
import os, sys
import shutil
import time

import torch
import torch.nn as nn
import torch.nn.parallel
import torch.backends.cudnn as cudnn
import torch.optim
import torch.utils.data
import torchvision.transforms as transforms
import torchvision.datasets as datasets
import torchvision.models
from utils import convert_secs2time, time_string, time_file_str
#from models import print_log
import models
import random
import numpy as np

model_names = sorted(name for name in models.__dict__
    if name.islower() and not name.startswith("__")
    and callable(models.__dict__[name]))

parser = argparse.ArgumentParser(description='PyTorch ImageNet Training')
parser.add_argument('data', metavar='DIR',
                    help='path to dataset')
parser.add_argument('--save_dir', type=str, default='./', help='Folder to save checkpoints and log.')
parser.add_argument('--arch', '-a', metavar='ARCH', default='resnet18',
                    choices=model_names,
                    help='model architecture: ' +
                        ' | '.join(model_names) +
                        ' (default: resnet18)')
parser.add_argument('-j', '--workers', default=4, type=int, metavar='N', help='number of data loading workers (default: 4)')
parser.add_argument('--epochs', default=100, type=int, metavar='N', help='number of total epochs to run')
parser.add_argument('--start-epoch', default=0, type=int, metavar='N', help='manual epoch number (useful on restarts)')
parser.add_argument('-b', '--batch-size', default=256, type=int, metavar='N', help='mini-batch size (default: 256)')
parser.add_argument('--lr', '--learning-rate', default=0.1, type=float, metavar='LR', help='initial learning rate')
parser.add_argument('--momentum', default=0.9, type=float, metavar='M', help='momentum')
parser.add_argument('--weight-decay', '--wd', default=1e-4, type=float, metavar='W', help='weight decay (default: 1e-4)')
parser.add_argument('--print-freq', '-p', default=200, type=int, metavar='N', help='print frequency (default: 100)')
parser.add_argument('--resume', default='', type=str, metavar='PATH', help='path to latest checkpoint (default: none)')
parser.add_argument('-e', '--evaluate', dest='evaluate', action='store_true', help='evaluate model on validation set')

args = parser.parse_args()
args.use_cuda = torch.cuda.is_available()

args.prefix = time_file_str()

def main():
    best_prec1 = 0

    if not os.path.isdir(args.save_dir):
      os.makedirs(args.save_dir)
    log = open(os.path.join(args.save_dir, '{}.{}.log'.format(args.arch,args.prefix)), 'w')

    # version information
    print_log("PyThon  version : {}".format(sys.version.replace('\n', ' ')), log)
    print_log("PyTorch version : {}".format(torch.__version__), log)
    print_log("cuDNN   version : {}".format(torch.backends.cudnn.version()), log)
    print_log("Vision  version : {}".format(torchvision.__version__), log)
    # create model
    print_log("=> creating model '{}'".format(args.arch), log)
    model = models.__dict__[args.arch](pretrained=False)
    print_log("=> Model : {}".format(model), log)
    print_log("=> parameter : {}".format(args), log)

    if args.arch.startswith('alexnet') or args.arch.startswith('vgg'):
      model.features = torch.nn.DataParallel(model.features)
      model.cuda()
    else:
      model = torch.nn.DataParallel(model).cuda()

    # define loss function (criterion) and optimizer
    criterion = nn.CrossEntropyLoss().cuda()

    optimizer = torch.optim.SGD(model.parameters(), args.lr,
                                momentum=args.momentum,
                                weight_decay=args.weight_decay,
                                nesterov=True)

    # optionally resume from a checkpoint
    if args.resume:
        if os.path.isfile(args.resume):
            print_log("=> loading checkpoint '{}'".format(args.resume), log)
            checkpoint = torch.load(args.resume)
            args.start_epoch = checkpoint['epoch']
            best_prec1 = checkpoint['best_prec1']
            model.load_state_dict(checkpoint['state_dict'])
            optimizer.load_state_dict(checkpoint['optimizer'])
            print_log("=> loaded checkpoint '{}' (epoch {})".format(args.resume, checkpoint['epoch']), log)
        else:
            print_log("=> no checkpoint found at '{}'".format(args.resume), log)

    cudnn.benchmark = True

    # Data loading code
    traindir = os.path.join(args.data, 'train')
    valdir = os.path.join(args.data, 'val')
    normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                     std=[0.229, 0.224, 0.225])

    train_dataset = datasets.ImageFolder(
        traindir,
        transforms.Compose([
            transforms.RandomResizedCrop(224),
            transforms.RandomHorizontalFlip(),
            transforms.ToTensor(),
            normalize,
        ]))

    train_loader = torch.utils.data.DataLoader(
        train_dataset, batch_size=args.batch_size, shuffle=True,
        num_workers=args.workers, pin_memory=True, sampler=None)

    val_loader = torch.utils.data.DataLoader(
        datasets.ImageFolder(valdir, transforms.Compose([
            transforms.Resize(256),
            transforms.CenterCrop(224),
            transforms.ToTensor(),
            normalize,
        ])),
        batch_size=args.batch_size, shuffle=False,
        num_workers=args.workers, pin_memory=True)

    if args.evaluate:
        validate(val_loader, model, criterion)
        return

    filename = os.path.join(args.save_dir, 'checkpoint.{}.{}.pth.tar'.format(args.arch, args.prefix))
    bestname = os.path.join(args.save_dir, 'best.{}.{}.pth.tar'.format(args.arch, args.prefix))

    start_time = time.time()
    epoch_time = AverageMeter()
    for epoch in range(args.start_epoch, args.epochs):
        adjust_learning_rate(optimizer, epoch)

        need_hour, need_mins, need_secs = convert_secs2time(epoch_time.val * (args.epochs-epoch))
        need_time = '[Need: {:02d}:{:02d}:{:02d}]'.format(need_hour, need_mins, need_secs)
        print_log(' [{:s}] :: {:3d}/{:3d} ----- [{:s}] {:s}'.format(args.arch, epoch, args.epochs, time_string(), need_time), log)

        # train for one epoch
        train(train_loader, model, criterion, optimizer, epoch, log)
        # evaluate on validation set
        val_acc_2 = validate(val_loader, model, criterion, log)

        # remember best prec@1 and save checkpoint
        is_best = val_acc_2 > best_prec1
        best_prec1 = max(val_acc_2, best_prec1)
        save_checkpoint({
            'epoch': epoch + 1,
            'arch': args.arch,
            'state_dict': model.state_dict(),
            'best_prec1': best_prec1,
            'optimizer' : optimizer.state_dict(),
        }, is_best, filename, bestname)
        # measure elapsed time
        epoch_time.update(time.time() - start_time)
        start_time = time.time()
    log.close()


def train(train_loader, model, criterion, optimizer, epoch, log):
    batch_time = AverageMeter()
    data_time = AverageMeter()
    losses = AverageMeter()
    top1 = AverageMeter()
    top5 = AverageMeter()

    # switch to train mode
    model.train()

    end = time.time()
    for i, (input, target) in enumerate(train_loader):
        # measure data loading time
        data_time.update(time.time() - end)

        target = target.cuda(async=True)
        input_var = torch.autograd.Variable(input)
        target_var = torch.autograd.Variable(target)

        # compute output
        output = model(input_var)
        loss = criterion(output, target_var)

        # measure accuracy and record loss
        prec1, prec5 = accuracy(output.data, target, topk=(1, 5))
        losses.update(loss.data[0], input.size(0))
        top1.update(prec1[0], input.size(0))
        top5.update(prec5[0], input.size(0))

        # compute gradient and do SGD step
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        # measure elapsed time
        batch_time.update(time.time() - end)
        end = time.time()

        if i % args.print_freq == 0:
            print_log('Epoch: [{0}][{1}/{2}]\t'
                  'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
                  'Data {data_time.val:.3f} ({data_time.avg:.3f})\t'
                  'Loss {loss.val:.4f} ({loss.avg:.4f})\t'
                  'Prec@1 {top1.val:.3f} ({top1.avg:.3f})\t'
                  'Prec@5 {top5.val:.3f} ({top5.avg:.3f})'.format(
                   epoch, i, len(train_loader), batch_time=batch_time,
                   data_time=data_time, loss=losses, top1=top1, top5=top5), log)


def validate(val_loader, model, criterion, log):
    batch_time = AverageMeter()
    losses = AverageMeter()
    top1 = AverageMeter()
    top5 = AverageMeter()

    # switch to evaluate mode
    model.eval()

    end = time.time()
    for i, (input, target) in enumerate(val_loader):
        target = target.cuda(async=True)
        input_var = torch.autograd.Variable(input, volatile=True)
        target_var = torch.autograd.Variable(target, volatile=True)

        # compute output
        output = model(input_var)
        loss = criterion(output, target_var)

        # measure accuracy and record loss
        prec1, prec5 = accuracy(output.data, target, topk=(1, 5))
        losses.update(loss.data[0], input.size(0))
        top1.update(prec1[0], input.size(0))
        top5.update(prec5[0], input.size(0))

        # measure elapsed time
        batch_time.update(time.time() - end)
        end = time.time()

        if i % args.print_freq == 0:
            print_log('Test: [{0}/{1}]\t'
                  'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
                  'Loss {loss.val:.4f} ({loss.avg:.4f})\t'
                  'Prec@1 {top1.val:.3f} ({top1.avg:.3f})\t'
                  'Prec@5 {top5.val:.3f} ({top5.avg:.3f})'.format(
                   i, len(val_loader), batch_time=batch_time, loss=losses,
                   top1=top1, top5=top5), log)

    print_log(' * Prec@1 {top1.avg:.3f} Prec@5 {top5.avg:.3f} Error@1 {error1:.3f}'.format(top1=top1, top5=top5, error1=100-top1.avg), log)

    return top1.avg


def save_checkpoint(state, is_best, filename, bestname):
    torch.save(state, filename)
    if is_best:
        shutil.copyfile(filename, bestname)

def print_log(print_string, log):
    print("{}".format(print_string))
    log.write('{}\n'.format(print_string))
    log.flush()
  
  
class AverageMeter(object):
    """Computes and stores the average and current value"""
    def __init__(self):
        self.reset()

    def reset(self):
        self.val = 0
        self.avg = 0
        self.sum = 0
        self.count = 0

    def update(self, val, n=1):
        self.val = val
        self.sum += val * n
        self.count += n
        self.avg = self.sum / self.count


def adjust_learning_rate(optimizer, epoch):
    """Sets the learning rate to the initial LR decayed by 10 every 30 epochs"""
    lr = args.lr * (0.1 ** (epoch // 30))
    for param_group in optimizer.param_groups:
        param_group['lr'] = lr


def accuracy(output, target, topk=(1,)):
    """Computes the precision@k for the specified values of k"""
    maxk = max(topk)
    batch_size = target.size(0)

    _, pred = output.topk(maxk, 1, True, True)
    pred = pred.t()
    correct = pred.eq(target.view(1, -1).expand_as(pred))

    res = []
    for k in topk:
        correct_k = correct[:k].view(-1).float().sum(0, keepdim=True)
        res.append(correct_k.mul_(100.0 / batch_size))
    return res


if __name__ == '__main__':
    main()