test.py

# 2019.07.24-Changed for testing full-stack filters
#            Huawei Technologies Co., Ltd. <foss@huawei.com>
import argparse
import os
import time
import numpy as np

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
from torch.utils.data import dataloader

# import our package
from mask_conv import ortho_loss
import mask_vgg

parser = argparse.ArgumentParser(description='Full-stack Filters for CIFAR10 in pytorch')
parser.add_argument('--arch', '-a', metavar='ARCH', default='resnet20',
                    help='model architecture: (default: resnet32)')
parser.add_argument('-j', '--workers', default=4, type=int, metavar='N',
                    help='number of data loading workers (default: 4)')
parser.add_argument('-b', '--batch-size', default=128, type=int,
                    metavar='N', help='mini-batch size (default: 128)')
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=20, type=int,
                    metavar='N', help='print frequency (default: 20)')
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')
parser.add_argument('--pretrained', dest='pretrained', action='store_true',
                    help='use pre-trained model')
parser.add_argument('--data-dir', dest='data_dir',
                    help='The directory used to save the dataset',
                    default='/tmp/hankai/data', type=str)


def main():
    global args
    args = parser.parse_args()
    print(args)

    model = torch.nn.DataParallel(mask_vgg.VGG('VGG16', r=64))
    model.cuda()

    # optionally resume from a checkpoint
    if args.resume:
        if os.path.isfile(args.resume):
            print("=> loading checkpoint '{}'".format(args.resume))
            checkpoint = torch.load(args.resume)
            best_prec1 = checkpoint['best_prec1']
            new_state_dict = checkpoint['state_dict']
            for param_tensor in new_state_dict:
                if 'mask' in param_tensor:
                    new_state_dict[param_tensor] = new_state_dict[param_tensor].to(torch.float32)-0.5
            model.load_state_dict(new_state_dict)
        else:
            print("=> no checkpoint found at '{}'".format(args.resume))

    cudnn.benchmark = True

    normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                     std=[0.229, 0.224, 0.225])

    val_loader = torch.utils.data.DataLoader(
        datasets.CIFAR10(root=args.data_dir, train=False, transform=transforms.Compose([
            transforms.ToTensor(),
            normalize,
        ]), download=True),
        batch_size=128, shuffle=False,
        num_workers=args.workers, pin_memory=True)

    # define loss function (criterion) and pptimizer
    criterion = nn.CrossEntropyLoss().cuda()
    # evaluate
    validate(val_loader, model, criterion)


def validate(val_loader, model, criterion):
    """
    Run evaluation
    """
    batch_time = AverageMeter()
    losses = AverageMeter()
    top1 = 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).cuda()
        target_var = torch.autograd.Variable(target, volatile=True)

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

        output = output.float()
        loss = loss.float()

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

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

        if i % args.print_freq == 0:
            print('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})'.format(
                      i, len(val_loader), batch_time=batch_time, loss=losses,
                      top1=top1))

    print(' * Prec@1 {top1.avg:.3f}'
          .format(top1=top1))

    return top1.avg


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 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)
        res.append(correct_k.mul_(100.0 / batch_size))
    return res


if __name__ == '__main__':
    main()