main_cls.py [291:378]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - momentum=args.momentum, weight_decay=args.weight_decay) # optionally resume from a checkpoint if args.resume: if os.path.isfile(args.resume): print("=> loading checkpoint '{}'".format(args.resume)) if args.gpu is None: checkpoint = torch.load(args.resume) else: # Map model to be loaded to specified single gpu. loc = 'cuda:{}'.format(args.gpu) checkpoint = torch.load(args.resume, map_location=loc) args.start_epoch = checkpoint['epoch'] best_acc1 = checkpoint['best_acc1'] if args.gpu is not None: # best_acc1 may be from a checkpoint from a different GPU best_acc1 = best_acc1.to(args.gpu) model.load_state_dict(checkpoint['state_dict']) optimizer.load_state_dict(checkpoint['optimizer']) print("=> loaded checkpoint '{}' (epoch {})" .format(args.resume, checkpoint['epoch'])) else: print("=> no checkpoint found at '{}'".format(args.resume)) cudnn.benchmark = True # Data loading code traindir = os.path.join(args.data, 'train') valdir = os.path.join(args.data, 'val') if args.trainindex is not None: index_info = os.path.join(args.data, 'indexes', args.trainindex) index_info = pd.read_csv(index_info) trainindex = index_info['Index'].tolist() else: trainindex = None train_transforms = data_transforms.get_transforms("DefaultTrain") train_dataset = datasets.ImageFolderWithIndex( traindir, trainindex, train_transforms) if args.distributed: train_sampler = torch.utils.data.distributed.DistributedSampler(train_dataset) else: train_sampler = None train_loader = torch.utils.data.DataLoader( train_dataset, batch_size=args.batch_size, shuffle=(train_sampler is None), num_workers=args.workers, pin_memory=True, sampler=train_sampler) val_transforms = data_transforms.get_transforms("DefaultVal") val_loader = torch.utils.data.DataLoader( datasets.ImageFolder(valdir, val_transforms), batch_size=args.batch_size, shuffle=False, num_workers=args.workers, pin_memory=True) if args.evaluate: validate(val_loader, model, criterion, args) return best_epoch = args.start_epoch for epoch in range(args.start_epoch, args.epochs): if args.distributed: train_sampler.set_epoch(epoch) adjust_learning_rate(optimizer, epoch, args) # train for one epoch train(train_loader, model, criterion, optimizer, epoch, args) if (epoch + 1) % args.eval_freq == 0: # evaluate on validation set acc1 = validate(val_loader, model, criterion, args) # remember best acc@1 and save checkpoint is_best = acc1 > best_acc1 best_acc1 = max(acc1, best_acc1) if is_best: best_epoch = epoch if not args.multiprocessing_distributed or (args.multiprocessing_distributed and args.rank % ngpus_per_node == 0): save_checkpoint({ 'epoch': epoch + 1, 'arch': args.arch, 'state_dict': model.state_dict(), 'best_acc1': best_acc1, 'optimizer': optimizer.state_dict(), }, is_best) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - main_lincls.py [253:340]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - momentum=args.momentum, weight_decay=args.weight_decay) # optionally resume from a checkpoint if args.resume: if os.path.isfile(args.resume): print("=> loading checkpoint '{}'".format(args.resume)) if args.gpu is None: checkpoint = torch.load(args.resume) else: # Map model to be loaded to specified single gpu. loc = 'cuda:{}'.format(args.gpu) checkpoint = torch.load(args.resume, map_location=loc) args.start_epoch = checkpoint['epoch'] best_acc1 = checkpoint['best_acc1'] if args.gpu is not None: # best_acc1 may be from a checkpoint from a different GPU best_acc1 = best_acc1.to(args.gpu) model.load_state_dict(checkpoint['state_dict']) optimizer.load_state_dict(checkpoint['optimizer']) print("=> loaded checkpoint '{}' (epoch {})" .format(args.resume, checkpoint['epoch'])) else: print("=> no checkpoint found at '{}'".format(args.resume)) cudnn.benchmark = True # Data loading code traindir = os.path.join(args.data, 'train') valdir = os.path.join(args.data, 'val') if args.trainindex is not None: index_info = os.path.join(args.data, 'indexes', args.trainindex) index_info = pd.read_csv(index_info) trainindex = index_info['Index'].tolist() else: trainindex = None train_transforms = data_transforms.get_transforms("DefaultTrain") train_dataset = datasets.ImageFolderWithIndex( traindir, trainindex, train_transforms) if args.distributed: train_sampler = torch.utils.data.distributed.DistributedSampler(train_dataset) else: train_sampler = None train_loader = torch.utils.data.DataLoader( train_dataset, batch_size=args.batch_size, shuffle=(train_sampler is None), num_workers=args.workers, pin_memory=True, sampler=train_sampler) val_transforms = data_transforms.get_transforms("DefaultVal") val_loader = torch.utils.data.DataLoader( datasets.ImageFolder(valdir, val_transforms), batch_size=args.batch_size, shuffle=False, num_workers=args.workers, pin_memory=True) if args.evaluate: validate(val_loader, model, criterion, args) return best_epoch = args.start_epoch for epoch in range(args.start_epoch, args.epochs): if args.distributed: train_sampler.set_epoch(epoch) adjust_learning_rate(optimizer, epoch, args) # train for one epoch train(train_loader, model, criterion, optimizer, epoch, args) if (epoch + 1) % args.eval_freq == 0: # evaluate on validation set acc1 = validate(val_loader, model, criterion, args) # remember best acc@1 and save checkpoint is_best = acc1 > best_acc1 best_acc1 = max(acc1, best_acc1) if is_best: best_epoch = epoch if not args.multiprocessing_distributed or (args.multiprocessing_distributed and args.rank % ngpus_per_node == 0): save_checkpoint({ 'epoch': epoch + 1, 'arch': args.arch, 'state_dict': model.state_dict(), 'best_acc1': best_acc1, 'optimizer': optimizer.state_dict(), }, is_best) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -