# -*- coding: utf-8 -*- # (C) Copyright IBM 2019. # # This code is licensed under the Apache License, Version 2.0. You may # obtain a copy of this license in the LICENSE file in the root directory # of this source tree or at http://www.apache.org/licenses/LICENSE-2.0. # # Any modifications or derivative works of this code must retain this # copyright notice, and modified files need to carry a notice indicating # that they have been altered from the originals. import time from PIL import Image import multiprocessing import torch import torch.nn as nn import torch.nn.parallel import torch.optim import torch.utils.data import torch.utils.data.distributed import torchvision.transforms as transforms import torchvision.datasets as datasets from tqdm import tqdm 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""" with torch.no_grad(): 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 def get_augmentor(is_train, image_size, strong=False): augments = [] if is_train: if strong: augments.append(transforms.RandomRotation(10)) augments += [ transforms.RandomResizedCrop(image_size, interpolation=Image.BILINEAR), transforms.ColorJitter(brightness=0.4, contrast=0.4, saturation=0.4), transforms.RandomHorizontalFlip() ] else: augments += [ transforms.Resize(int(image_size / 0.875 + 0.5) if image_size == 224 else image_size, interpolation=Image.BILINEAR), transforms.CenterCrop(image_size) ] augments += [ transforms.ToTensor(), transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) ] augmentor = transforms.Compose(augments) return augmentor def get_imagenet_dataflow(is_train, data_dir, batch_size, augmentor, workers=18, is_distributed=False): workers = min(workers, multiprocessing.cpu_count()) sampler = None shuffle = False if is_train: dataset = datasets.ImageFolder(data_dir, augmentor) sampler = torch.utils.data.distributed.DistributedSampler(dataset) if is_distributed else None shuffle = sampler is None else: dataset = datasets.ImageFolder(data_dir, augmentor) data_loader = torch.utils.data.DataLoader(dataset, batch_size=batch_size, shuffle=shuffle, num_workers=workers, pin_memory=True, sampler=sampler) return data_loader def train(data_loader, model, criterion, optimizer, epoch, steps_per_epoch=99999999999): batch_time = AverageMeter() data_time = AverageMeter() losses = AverageMeter() top1 = AverageMeter() top5 = AverageMeter() # switch to train mode model.train() end = time.time() num_batch = 0 with tqdm(total=len(data_loader)) as t_bar: for i, (input, target) in enumerate(data_loader): # measure data loading time data_time.update(time.time() - end) # compute output output = model(input) target = target.cuda(non_blocking=True) loss = criterion(output, target) # measure accuracy and record loss prec1, prec5 = accuracy(output, target, topk=(1, 5)) losses.update(loss.item(), 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() num_batch += 1 t_bar.update(1) if i > steps_per_epoch: break return top1.avg, top5.avg, losses.avg, batch_time.avg, data_time.avg, num_batch def validate(data_loader, model, criterion): batch_time = AverageMeter() losses = AverageMeter() top1 = AverageMeter() top5 = AverageMeter() # switch to evaluate mode model.eval() with torch.no_grad(), tqdm(total=len(data_loader)) as t_bar: end = time.time() for i, (input, target) in enumerate(data_loader): target = target.cuda(non_blocking=True) # compute output output = model(input) loss = criterion(output, target) # measure accuracy and record loss prec1, prec5 = accuracy(output, target, topk=(1, 5)) losses.update(loss.item(), 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() t_bar.update(1) return top1.avg, top5.avg, losses.avg, batch_time.avg