def train(train_loader, model, criterion, optimizer, epoch, args, print_func): batch_time = CNN_utils.AverageMeter() data_time = CNN_utils.AverageMeter() losses = CNN_utils.AverageMeter() top1 = CNN_utils.AverageMeter() top5 = CNN_utils.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) if args.gpu is not None: input = input.cuda(args.gpu, non_blocking=True) target = target.cuda(args.gpu, non_blocking=True) # compute output output = model(input) loss = criterion(output, target) # measure accuracy and record loss kout = 5 if args.num_classes < kout * 2: kout = args.num_classes // 2 if kout < 1: kout = 1 prec1, prec5 = CNN_utils.accuracy(output, target, topk=(1, kout)) 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() if i % args.print_freq == 0: print_func('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@{kout} {top5.val:.3f} ({top5.avg:.3f})'.format( epoch, i, len(train_loader), batch_time=batch_time, data_time=data_time, loss=losses, top1=top1, kout=kout, top5=top5))
def train(train_loader, model, criterion, optimizer, epoch, args, print_func): batch_time = CNN_utils.AverageMeter() data_time = CNN_utils.AverageMeter() losses = CNN_utils.AverageMeter() top1 = CNN_utils.AverageMeter() top5 = CNN_utils.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) if args.gpu is not None: input = input.cuda(args.gpu, non_blocking=True) target = target.cuda(args.gpu, non_blocking=True) # target_idx = target.nonzero() [:,1] # compute output output = model(input) # log_softmax_output = F.log_softmax(output, dim=1) # # loss = - torch.sum(log_softmax_output * target) / output.shape[0] loss = criterion(output, target) losses.update(loss.item(), input.size(0)) prec1 = CNN_utils.accuracy(output, target, topk=(1, 1)) top1.update(prec1[0].item(), input.size(0)) # top5.update(prec5[0], input.size(0)) 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_func('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@{kout} {top5.val:.3f} ({top5.avg:.3f})'.format( epoch, i, len(train_loader), batch_time=batch_time, data_time=data_time, loss=losses, top1=top1, kout=5, top5=top5))
def train(train_loader, model, criterion, optimizer, epoch, args, print_func): batch_time = CNN_utils.AverageMeter() data_time = CNN_utils.AverageMeter() losses = CNN_utils.AverageMeter() top1 = CNN_utils.AverageMeter() topX = CNN_utils.AverageMeter() kout = args.topX or args.num_classes // 2 # switch to train mode model.train() if args.fix_BN: CNN_utils.fix_BN(model) end = time.time() for i, (input, target) in enumerate(train_loader): # measure data loading time data_time.update(time.time() - end) if args.gpu is not None: input = input.cuda(args.gpu, non_blocking=True) target = target.cuda(args.gpu, non_blocking=True) # target_idx = target.nonzero() [:,1] # compute output output = model(input) loss = criterion(output, target) losses.update(loss.item(), input.size(0)) prec1, precX = CNN_utils.accuracy(output, target, topk=(1, kout)) top1.update(prec1[0], input.size(0)) topX.update(precX[0], input.size(0)) 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_func('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@{kout} {topX.val:.3f} ({topX.avg:.3f})'.format( epoch, i, len(train_loader), batch_time=batch_time, data_time=data_time, loss=losses, top1=top1, kout=kout, topX=topX))
def validate(val_loader, model, criterion, args, print_func): if val_loader is None: return 0, 0 batch_time = CNN_utils.AverageMeter() losses = CNN_utils.AverageMeter() top1 = CNN_utils.AverageMeter() topX = CNN_utils.AverageMeter() kout = args.topX or args.num_classes // 2 # switch to evaluate mode model.eval() with torch.no_grad(): end = time.time() for i, (input, target) in enumerate(val_loader): if args.gpu is not None: input = input.cuda(args.gpu, non_blocking=True) target = target.cuda(args.gpu, non_blocking=True) # compute output output = model(input) loss = criterion(output, target) losses.update(loss.item(), input.size(0)) prec1, precX = CNN_utils.accuracy(output, target, topk=(1, kout)) top1.update(prec1[0], input.size(0)) topX.update(precX[0], input.size(0)) # measure elapsed time batch_time.update(time.time() - end) end = time.time() if i % args.print_freq == 0: print_func('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@{kout} {topX.val:.3f} ({topX.avg:.3f})'.format( i, len(val_loader), batch_time=batch_time, loss=losses, top1=top1, kout=kout, topX = topX)) print_func(' * Prec@1 {top1.avg:.3f}' .format(top1=top1)) return top1.avg, losses.avg
def validate(val_loader, model, criterion, args, print_func): if val_loader is None: return 0, 0 batch_time = CNN_utils.AverageMeter() losses = CNN_utils.AverageMeter() top1 = CNN_utils.AverageMeter() # top5 = CNN_utils.AverageMeter() # switch to evaluate mode model.eval() with torch.no_grad(): end = time.time() for i, (input, target) in enumerate(val_loader): if args.gpu is not None: input = input.cuda(args.gpu, non_blocking=True) target = target.cuda(args.gpu, non_blocking=True) # compute output output = model(input) loss = criterion(output, target) # log_softmax_output = F.log_softmax(output, dim=1) # # loss = - torch.sum(log_softmax_output * target)/ output.shape[0] # measure accuracy and record loss prec1 = CNN_utils.accuracy(output, target, topk=(1, 1)) losses.update(loss.item(), input.size(0)) top1.update(prec1[0].item(), 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_func('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_func(' * Prec@1 {top1.avg:.3f}'.format(top1=top1)) return top1.avg, losses.avg
def train(train_loads_iter, train_loaders, model, criterion, optimizer, epoch, args, print_func): batch_time = CNN_utils.AverageMeter() data_time = CNN_utils.AverageMeter() losses = CNN_utils.AverageMeter() top1 = CNN_utils.AverageMeter() topX = CNN_utils.AverageMeter() # switch to train mode model.train() if args.fix_BN: CNN_utils.fix_BN(model) #args.lam = 2 / (1 + math.exp(-epoch / 100)) - 1 batch_iters = math.ceil(args.num_iter / args.batch_size) for i in range(batch_iters): start = time.time() l_loss = [] l_top1 = [] l_topX = [] optimizer.zero_grad() for ds in range(args.num_datasets): args.ind = ds kout = args.topX or args.class_len[args.ind] // 2 end = time.time() try: (input, target) = train_loads_iter[ds].next() except StopIteration: train_loads_iter[ds] = iter(train_loaders[ds]) (input, target) = train_loads_iter[ds].next() # measure data loading time data_time.update(time.time() - end) if args.gpu is not None: input = input.cuda(args.gpu, non_blocking=True) target = target.cuda(args.gpu, non_blocking=True) # compute output output = model(input) output_i = output[(args.class_len[args.ind] // 2) % 3] output_dom = output[-1].squeeze().cuda(args.gpu, non_blocking=True) loss = criterion(output_i, target) dom_target = torch.tensor( np.array([args.ind for _ in range(list(target.size())[0])]), dtype=torch.float).cuda(args.gpu, non_blocking=True) dtarget = dom_target.cuda(args.gpu, non_blocking=True) domain_loss = F.binary_cross_entropy_with_logits( dom_target, dtarget) total_loss = loss + domain_loss total_loss.backward() l_loss.append(loss.item() - args.lam * domain_loss.item()) prec1, precX = CNN_utils.accuracy(output_i, target, topk=(1, kout)) l_top1.append(prec1.item()) l_topX.append(precX.item()) losses.update(l_loss[-1], input.size(0)) top1.update(sum(l_top1) / len(l_top1), input.size(0)) topX.update(sum(l_topX) / len(l_topX), input.size(0)) #optimizer.zero_grad() #allloss_var.backward() optimizer.step() # measure elapsed time batch_time.update(time.time() - start) if i % args.print_freq == 0: print_func('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@X {topX.val:.3f} ({topX.avg:.3f})'.format( epoch, i, batch_iters, batch_time=batch_time, data_time=data_time, loss=losses, top1=top1, topX=topX))
def train(train_loads_iter, train_loaders, model, criterion, optimizer, epoch, args, print_func): batch_time = CNN_utils.AverageMeter() data_time = CNN_utils.AverageMeter() losses = CNN_utils.AverageMeter() top1 = CNN_utils.AverageMeter() topX = CNN_utils.AverageMeter() # switch to train mode model.train() if args.fix_BN: CNN_utils.fix_BN(model) batch_iters = math.ceil(args.num_iter / args.batch_size) for i in range(batch_iters): start = time.time() l_loss = [] l_top1 = [] l_topX = [] #allloss_var = 0 optimizer.zero_grad() for ds in range(args.num_datasets): args.ind = ds kout = args.topX or args.class_len[args.ind] // 2 end = time.time() try: (input, target) = train_loads_iter[ds].next() except StopIteration: train_loads_iter[ds] = iter(train_loaders[ds]) (input, target) = train_loads_iter[ds].next() # measure data loading time data_time.update(time.time() - end) if args.gpu is not None: input = input.cuda(args.gpu, non_blocking=True) target = target.cuda(args.gpu, non_blocking=True) # target_idx = target.nonzero() [:,1] # if torch.max(target) >= 0 and torch.max(target) < args.class_len[args.ind]: # compute output #print("Input shape {}".format(input.shape)) output = model(input) output_i = output[args.ind] #print("Output_i device {}".format(output_i.device)) loss = criterion(output_i, target) l_loss.append(loss.item()) #allloss_var += loss loss.backward() prec1, precX = CNN_utils.accuracy(output_i.detach(), target, topk=(1, kout)) l_top1.append(prec1.item()) l_topX.append(precX.item()) losses.update(sum(l_loss), input.size(0)) top1.update(sum(l_top1) / len(l_top1), input.size(0)) topX.update(sum(l_topX) / len(l_topX), input.size(0)) #optimizer.zero_grad() #allloss_var.backward() optimizer.step() # measure elapsed time batch_time.update(time.time() - start) if i % args.print_freq == 0: print_func('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@X {topX.val:.3f} ({topX.avg:.3f})'.format( epoch, i, batch_iters, batch_time=batch_time, data_time=data_time, loss=losses, top1=top1, topX=topX))