def validation(self, epoch): def _get_pred(batch_im): with torch.no_grad(): # metric.update also accepts list, so no need to gather results from multi gpus if self.args.multi_scale_eval: assert len(batch_im) <= torch.cuda.device_count( ), "Multi-scale testing only allows batch size <= number of GPUs" scattered_pred = self.ms_evaluator.parallel_forward( batch_im) else: outputs = self.model(batch_im) scattered_pred = [ out[0] for out in outputs ] if self.args.multi_gpu else [outputs[0]] return scattered_pred # Lazy creation if not hasattr(self, 'ms_evaluator'): self.ms_evaluator = MultiEvalModule(self.single_device_model, self.nclass, scales=self.args.eval_scales, crop=self.args.crop_eval) self.metric = utils.SegmentationMetric(self.nclass) self.model.eval() tbar = tqdm(self.valloader, desc='\r') for i, (batch_im, target) in enumerate(tbar): # No need to put target to GPU, since the metrics are calculated by numpy. # And no need to put data to GPU manually if we use data parallel. if not self.args.multi_gpu and not isinstance( batch_im, (list, tuple)): batch_im = batch_im.cuda() scattered_pred = _get_pred(batch_im) scattered_target = [] ind = 0 for p in scattered_pred: target_tmp = target[ind:ind + len(p)] # Multi-scale testing. In fact, len(target_tmp) == 1 if isinstance(target_tmp, (list, tuple)): assert len(target_tmp) == 1 target_tmp = torch.stack(target_tmp) scattered_target.append(target_tmp) ind += len(p) self.metric.update(scattered_target, scattered_pred) pixAcc, mIoU = self.metric.get() tbar.set_description('ep {}, pixAcc: {:.4f}, mIoU: {:.4f}'.format( epoch + 1, pixAcc, mIoU)) return self.metric.get()
def test(args): # output folder outdir = args.save_folder if not os.path.exists(outdir): os.makedirs(outdir) # data transforms input_transform = transform.Compose([ transform.ToTensor(), transform.Normalize([.485, .456, .406], [.229, .224, .225]) ]) # dataset testset = get_segmentation_dataset(args.dataset, split=args.split, mode=args.mode, transform=input_transform) # dataloader loader_kwargs = {'num_workers': args.workers, 'pin_memory': True} \ if args.cuda else {} test_data = data.DataLoader(testset, batch_size=args.test_batch_size, drop_last=False, shuffle=False, collate_fn=test_batchify_fn, **loader_kwargs) # model if args.model_zoo is not None: model = get_model(args.model_zoo, pretrained=True) else: model = get_segmentation_model(args.model, dataset=args.dataset, backbone=args.backbone, dilated=args.dilated, multi_grid=args.multi_grid, stride=args.stride, lateral=args.lateral, jpu=args.jpu, aux=args.aux, se_loss=args.se_loss, norm_layer=BatchNorm, base_size=args.base_size, crop_size=args.crop_size) # resuming checkpoint if args.resume is None or not os.path.isfile(args.resume): raise RuntimeError("=> no checkpoint found at '{}'".format( args.resume)) checkpoint = torch.load(args.resume) # strict=False, so that it is compatible with old pytorch saved models model.load_state_dict(checkpoint['state_dict']) print("=> loaded checkpoint '{}' (epoch {})".format( args.resume, checkpoint['epoch'])) # print(model) scales = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0, 2.25] if args.dataset == 'citys' else \ [0.5, 0.75, 1.0, 1.25, 1.5, 1.75] if not args.ms: scales = [1.0] evaluator = MultiEvalModule(model, testset.num_class, scales=scales, flip=args.ms).cuda() evaluator.eval() metric = utils.SegmentationMetric(testset.num_class) tbar = tqdm(test_data) for i, (image, dst) in enumerate(tbar): if 'val' in args.mode: with torch.no_grad(): predicts = evaluator.parallel_forward(image) metric.update(dst, predicts) pixAcc, mIoU = metric.get() tbar.set_description('pixAcc: %.4f, mIoU: %.4f' % (pixAcc, mIoU)) else: # with torch.no_grad(): # outputs = evaluator.parallel_forward(image) # predicts = [testset.make_pred(torch.max(output, 1)[1].cpu().numpy()) # for output in outputs] # for predict, impath in zip(predicts, dst): # mask = utils.get_mask_pallete(predict, args.dataset) # outname = os.path.splitext(impath)[0] + '.png' # mask.save(os.path.join(outdir, outname)) with torch.no_grad(): outputs = evaluator.parallel_forward(image) # predicts = [testset.make_pred(torch.max(output, 1)[1].cpu().numpy()) # for output in outputs] predicts = [ torch.softmax(output, 1).cpu().numpy() for output in outputs ] for predict, impath in zip(predicts, dst): # mask = utils.get_mask_pallete(predict, args.dataset) import numpy as np from PIL import Image mask = Image.fromarray( (predict[0, 1, :, :] * 255).astype(np.uint8)) outname = os.path.splitext(impath)[0] + '.bmp' mask.save(os.path.join(outdir, outname))
def test(args): # output folder outdir = 'outdir' if not os.path.exists(outdir): os.makedirs(outdir) # data transforms input_transform = transform.Compose([ transform.ToTensor(), transform.Normalize([.485, .456, .406], [.229, .224, .225]) ]) # dataset if args.eval: testset = get_dataset(args.dataset, split='val', mode='testval', transform=input_transform) elif args.test_val: testset = get_dataset(args.dataset, split='val', mode='test', transform=input_transform) else: testset = get_dataset(args.dataset, split='test', mode='test', transform=input_transform) # dataloader loader_kwargs = {'num_workers': args.workers, 'pin_memory': True} \ if args.cuda else {} test_data = data.DataLoader(testset, batch_size=args.test_batch_size, drop_last=False, shuffle=False, collate_fn=test_batchify_fn, **loader_kwargs) # model pretrained = args.resume is None and args.verify is None if args.model_zoo is not None: model = get_model(args.model_zoo, pretrained=pretrained) model.base_size = args.base_size model.crop_size = args.crop_size else: # my model_kwargs = {} if args.choice_indices is not None: assert 'alone_resnest50' in args.backbone model_kwargs['choice_indices'] = args.choice_indices # model = get_segmentation_model( args.model, dataset=args.dataset, backbone=args.backbone, aux=args.aux, se_loss=args.se_loss, norm_layer=torch.nn.BatchNorm2d if args.acc_bn else SyncBatchNorm, base_size=args.base_size, crop_size=args.crop_size, **model_kwargs) # resuming checkpoint if args.verify is not None and os.path.isfile(args.verify): print("=> loading checkpoint '{}'".format(args.verify)) model.load_state_dict(torch.load(args.verify, map_location='cpu')) elif args.resume is not None and os.path.isfile(args.resume): checkpoint = torch.load(args.resume, map_location='cpu') # strict=False, so that it is compatible with old pytorch saved models model.load_state_dict(checkpoint['state_dict']) print("=> loaded checkpoint '{}'".format(args.resume)) elif not pretrained: raise RuntimeError("=> no checkpoint found") print(model) if args.acc_bn: from encoding.utils.precise_bn import update_bn_stats data_kwargs = { 'transform': input_transform, 'base_size': args.base_size, 'crop_size': args.crop_size } trainset = get_dataset(args.dataset, split=args.train_split, mode='train', **data_kwargs) trainloader = data.DataLoader(ReturnFirstClosure(trainset), batch_size=args.batch_size, drop_last=True, shuffle=True, **loader_kwargs) print('Reseting BN statistics') #model.apply(reset_bn_statistics) model.cuda() update_bn_stats(model, trainloader) if args.export: torch.save(model.state_dict(), args.export + '.pth') return scales = [0.75, 1.0, 1.25, 1.5, 1.75, 2.0, 2.25] if args.dataset == 'citys' else \ [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]#, 2.0 evaluator = MultiEvalModule(model, testset.num_class, scales=scales).cuda() evaluator.eval() metric = utils.SegmentationMetric(testset.num_class) tbar = tqdm(test_data) for i, (image, dst) in enumerate(tbar): if args.eval: with torch.no_grad(): predicts = evaluator.parallel_forward(image) metric.update(dst, predicts) pixAcc, mIoU = metric.get() tbar.set_description('pixAcc: %.4f, mIoU: %.4f' % (pixAcc, mIoU)) else: with torch.no_grad(): outputs = evaluator.parallel_forward(image) predicts = [ testset.make_pred(torch.max(output, 1)[1].cpu().numpy()) for output in outputs ] for predict, impath in zip(predicts, dst): mask = utils.get_mask_pallete(predict, args.dataset) outname = os.path.splitext(impath)[0] + '.png' mask.save(os.path.join(outdir, outname)) if args.eval: print('pixAcc: %.4f, mIoU: %.4f' % (pixAcc, mIoU))
def test(args): # output folder outdir = 'outdir' if not os.path.exists(outdir): os.makedirs(outdir) # data transforms input_transform = transform.Compose([ transform.ToTensor(), transform.Normalize([.485, .456, .406], [.229, .224, .225]) ]) # dataset data_kwargs = {'root': args.data_root} if args.eval: testset = get_segmentation_dataset(args.dataset, split='val', mode='testval', transform=input_transform, **data_kwargs) elif args.test_val: testset = get_segmentation_dataset(args.dataset, split='val', mode='test', transform=input_transform, **data_kwargs) else: testset = get_segmentation_dataset(args.dataset, split='test', mode='test', transform=input_transform, **data_kwargs) # dataloader loader_kwargs = {'num_workers': args.workers, 'pin_memory': True} \ if args.cuda else {} test_data = data.DataLoader(testset, batch_size=args.test_batch_size, drop_last=False, shuffle=False, collate_fn=test_batchify_fn, **loader_kwargs) # model if args.model_zoo is not None: model = get_model(args.model_zoo, pretrained=True) #model.base_size = args.base_size #model.crop_size = args.crop_size else: model = get_segmentation_model(args.model, dataset=args.dataset, backbone=args.backbone, aux=args.aux, se_loss=args.se_loss, norm_layer=SyncBatchNorm, base_size=args.base_size, crop_size=args.crop_size) # resuming checkpoint if args.resume is None or not os.path.isfile(args.resume): raise RuntimeError("=> no checkpoint found at '{}'".format( args.resume)) checkpoint = torch.load(args.resume) # strict=False, so that it is compatible with old pytorch saved models model.load_state_dict(checkpoint['state_dict']) print("=> loaded checkpoint '{}' (epoch {})".format( args.resume, checkpoint['epoch'])) print(model) # scales = [0.75, 1.0, 1.25, 1.5, 1.75, 2.0, 2.25] if args.dataset == 'citys' else \ # [0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0] scales = [1.0] evaluator = MultiEvalModule(model, testset.num_class, scales=scales).cuda() evaluator.eval() metric = utils.SegmentationMetric(testset.num_class) tbar = tqdm(test_data) for i, (image, dst) in enumerate(tbar): if args.eval: with torch.no_grad(): predicts = evaluator.parallel_forward(image) metric.update(dst, predicts) pixAcc, mIoU = metric.get() tbar.set_description('pixAcc: %.4f, mIoU: %.4f' % (pixAcc, mIoU)) else: with torch.no_grad(): outputs = evaluator.parallel_forward(image) predicts = [ testset.make_pred(torch.max(output, 1)[1].cpu().numpy()) for output in outputs ] for predict, impath in zip(predicts, dst): mask = utils.get_mask_pallete(predict, args.dataset) outname = os.path.splitext(impath)[0] + '.png' mask.save(os.path.join(outdir, outname))
def main_worker(gpu, ngpus_per_node, args): global best_pred args.gpu = gpu args.rank = args.rank * ngpus_per_node + gpu print('rank: {} / {}'.format(args.rank, args.world_size)) dist.init_process_group(backend=args.dist_backend, init_method=args.dist_url, world_size=args.world_size, rank=args.rank) torch.cuda.set_device(args.gpu) torch.manual_seed(args.seed) torch.cuda.manual_seed(args.seed) cudnn.benchmark = True # data transforms input_transform = transform.Compose([ transform.ToTensor(), transform.Normalize([.485, .456, .406], [.229, .224, .225]) ]) # dataset data_kwargs = { 'transform': input_transform, 'base_size': args.base_size, 'crop_size': args.crop_size } trainset = get_dataset(args.dataset, split=args.train_split, mode='train', **data_kwargs) valset = get_dataset(args.dataset, split='val', mode='val', **data_kwargs) train_sampler = torch.utils.data.distributed.DistributedSampler(trainset) val_sampler = torch.utils.data.distributed.DistributedSampler( valset, shuffle=False) # dataloader loader_kwargs = { 'batch_size': args.batch_size, 'num_workers': args.workers, 'pin_memory': True } trainloader = data.DataLoader(trainset, sampler=train_sampler, drop_last=True, **loader_kwargs) valloader = data.DataLoader(valset, sampler=val_sampler, **loader_kwargs) nclass = trainset.num_class # model model_kwargs = {} if args.rectify: model_kwargs['rectified_conv'] = True model_kwargs['rectify_avg'] = args.rectify_avg model = get_segmentation_model(args.model, dataset=args.dataset, backbone=args.backbone, aux=args.aux, se_loss=args.se_loss, norm_layer=DistSyncBatchNorm, base_size=args.base_size, crop_size=args.crop_size, **model_kwargs) if args.gpu == 0: print(model) # optimizer using different LR params_list = [ { 'params': model.pretrained.parameters(), 'lr': args.lr }, ] if hasattr(model, 'head'): params_list.append({ 'params': model.head.parameters(), 'lr': args.lr * 10 }) if hasattr(model, 'auxlayer'): params_list.append({ 'params': model.auxlayer.parameters(), 'lr': args.lr * 10 }) optimizer = torch.optim.SGD(params_list, lr=args.lr, momentum=args.momentum, weight_decay=args.weight_decay) # optimizer = torch.optim.Adam(params_list, # lr=args.lr, # # momentum=args.momentum, # weight_decay=args.weight_decay) # criterions criterion = SegmentationLosses(se_loss=args.se_loss, aux=args.aux, nclass=nclass, se_weight=args.se_weight, aux_weight=args.aux_weight) # distributed data parallel model.cuda(args.gpu) criterion.cuda(args.gpu) model = DistributedDataParallel(model, device_ids=[args.gpu]) metric = utils.SegmentationMetric(nclass=nclass) # resuming checkpoint if args.resume is not None: if not os.path.isfile(args.resume): raise RuntimeError("=> no checkpoint found at '{}'".format( args.resume)) checkpoint = torch.load(args.resume) args.start_epoch = checkpoint['epoch'] model.module.load_state_dict(checkpoint['state_dict']) ''' checkpoint = torch.load(args.resume, map_location='cpu') args.start_epoch = checkpoint['epoch'] model.module.load_state_dict(checkpoint['state_dict']) model.cuda() ''' if not args.ft: optimizer.load_state_dict(checkpoint['optimizer']) best_pred = checkpoint['best_pred'] print("=> loaded checkpoint '{}' (epoch {})".format( args.resume, checkpoint['epoch'])) # clear start epoch if fine-tuning if args.ft: args.start_epoch = 0 # lr scheduler scheduler = utils.LR_Scheduler_Head(args.lr_scheduler, args.lr, args.epochs, len(trainloader)) # train_losses = [2.855, 2.513, 2.275, 2.128, 2.001, 1.875, 1.855, 1.916, 1.987, 1.915, 1.952] train_losses = [] def training(epoch): train_sampler.set_epoch(epoch) global best_pred train_loss = 0.0 model.train() tic = time.time() for i, (image, target) in enumerate(trainloader): scheduler(optimizer, i, epoch, best_pred) optimizer.zero_grad() outputs = model(image) target = target.cuda(args.gpu) loss = criterion(*outputs, target) loss.backward() optimizer.step() train_loss += loss.item() if i % 100 == 0 and args.gpu == 0: iter_per_sec = 100.0 / ( time.time() - tic) if i != 0 else 1.0 / (time.time() - tic) tic = time.time() print('Epoch: {}, Iter: {}, Speed: {:.3f} iter/sec, Train loss: {:.3f}'. \ format(epoch, i, iter_per_sec, train_loss / (i + 1))) train_losses.append(train_loss / len(trainloader)) if epoch > 1: if train_losses[epoch] < train_losses[epoch - 1]: utils.save_checkpoint( { 'epoch': epoch + 1, 'state_dict': model.module.state_dict(), 'optimizer': optimizer.state_dict(), 'best_pred': new_preds[(epoch - 1) // 10], }, args, False, filename='checkpoint_train.pth.tar') plt.plot(train_losses) plt.xlabel('Epoch') plt.ylabel('Train_loss') plt.title('Train_Loss') plt.grid() plt.savefig('./loss_fig/train_losses.pdf') plt.savefig('./loss_fig/train_losses.svg') plt.close() # p_m = [(0.3, 0.05), (0.23, 0.54)] # new_preds = [0.175, 0.392] p_m = [] new_preds = [] def validation(epoch): # Fast test during the training using single-crop only global best_pred is_best = False model.eval() metric.reset() for i, (image, target) in enumerate(valloader): with torch.no_grad(): pred = model(image)[0] target = target.cuda(args.gpu) metric.update(target, pred) if i % 100 == 0: all_metircs = metric.get_all() all_metircs = utils.torch_dist_sum(args.gpu, *all_metircs) pixAcc, mIoU = utils.get_pixacc_miou(*all_metircs) if args.gpu == 0: print('pixAcc: %.3f, mIoU1: %.3f' % (pixAcc, mIoU)) all_metircs = metric.get_all() all_metircs = utils.torch_dist_sum(args.gpu, *all_metircs) pixAcc, mIoU = utils.get_pixacc_miou(*all_metircs) if args.gpu == 0: print('pixAcc: %.3f, mIoU2: %.3f' % (pixAcc, mIoU)) p_m.append((pixAcc, mIoU)) plt.plot(p_m) plt.xlabel('10 Epoch') plt.ylabel('pixAcc, mIoU') plt.title('pixAcc, mIoU') plt.grid() plt.legend(('pixAcc', 'mIoU')) plt.savefig('./loss_fig/pixAcc_mIoU.pdf') plt.savefig('./loss_fig/pixAcc_mIoU.svg') plt.close() if args.eval: return new_pred = (pixAcc + mIoU) / 2 new_preds.append(new_pred) plt.plot(new_preds) plt.xlabel('10 Epoch') plt.ylabel('new_predication') plt.title('new_predication') plt.grid() plt.savefig('./loss_fig/new_predication.pdf') plt.savefig('./loss_fig/new_predication.svg') plt.close() if new_pred > best_pred: is_best = True best_pred = new_pred utils.save_checkpoint( { 'epoch': epoch + 1, 'state_dict': model.module.state_dict(), 'optimizer': optimizer.state_dict(), 'best_pred': best_pred, }, args, is_best, filename='checkpoint_train_{}.pth.tar'.format(epoch + 1)) if args.export: if args.gpu == 0: torch.save(model.module.state_dict(), args.export + '.pth') return if args.eval: validation(args.start_epoch) return if args.gpu == 0: print('Starting Epoch:', args.start_epoch) print('Total Epoches:', args.epochs) for epoch in range(args.start_epoch, args.epochs): tic = time.time() training(epoch) if epoch % 10 == 0 or epoch == args.epochs - 1: validation(epoch) elapsed = time.time() - tic if args.gpu == 0: print(f'Epoch: {epoch}, Time cost: {elapsed}') validation(epoch)
def main_worker(gpu, ngpus_per_node, args): global best_pred args.gpu = gpu args.rank = args.rank * ngpus_per_node + gpu print('rank: {} / {}'.format(args.rank, args.world_size)) dist.init_process_group(backend=args.dist_backend, init_method=args.dist_url, world_size=args.world_size, rank=args.rank) torch.cuda.set_device(args.gpu) torch.manual_seed(args.seed) torch.cuda.manual_seed(args.seed) cudnn.benchmark = True # data transforms input_transform = transform.Compose([ transform.ToTensor(), transform.Normalize([.485, .456, .406], [.229, .224, .225]) ]) # dataset data_kwargs = { 'transform': input_transform, 'base_size': args.base_size, 'crop_size': args.crop_size } trainset = get_dataset(args.dataset, split=args.train_split, mode='train', **data_kwargs) valset = get_dataset(args.dataset, split='val', mode='val', **data_kwargs) train_sampler = torch.utils.data.distributed.DistributedSampler(trainset) val_sampler = torch.utils.data.distributed.DistributedSampler( valset, shuffle=False) # dataloader loader_kwargs = { 'batch_size': args.batch_size, 'num_workers': args.workers, 'pin_memory': True } trainloader = data.DataLoader(trainset, sampler=train_sampler, drop_last=True, **loader_kwargs) valloader = data.DataLoader(valset, sampler=val_sampler, **loader_kwargs) nclass = trainset.num_class # model model_kwargs = {} if args.rectify: model_kwargs['rectified_conv'] = True model_kwargs['rectify_avg'] = args.rectify_avg model = get_segmentation_model(args.model, dataset=args.dataset, backbone=args.backbone, aux=args.aux, se_loss=args.se_loss, norm_layer=DistSyncBatchNorm, base_size=args.base_size, crop_size=args.crop_size, **model_kwargs) if args.gpu == 0: print(model) # optimizer using different LR params_list = [ { 'params': model.pretrained.parameters(), 'lr': args.lr }, ] if hasattr(model, 'head'): params_list.append({ 'params': model.head.parameters(), 'lr': args.lr * 10 }) if hasattr(model, 'auxlayer'): params_list.append({ 'params': model.auxlayer.parameters(), 'lr': args.lr * 10 }) optimizer = torch.optim.SGD(params_list, lr=args.lr, momentum=args.momentum, weight_decay=args.weight_decay) # criterions criterion = SegmentationLosses(se_loss=args.se_loss, aux=args.aux, nclass=nclass, se_weight=args.se_weight, aux_weight=args.aux_weight) # distributed data parallel model.cuda(args.gpu) criterion.cuda(args.gpu) model = DistributedDataParallel(model, device_ids=[args.gpu]) metric = utils.SegmentationMetric(nclass=nclass) # resuming checkpoint if args.resume is not None: if not os.path.isfile(args.resume): raise RuntimeError("=> no checkpoint found at '{}'".format( args.resume)) checkpoint = torch.load(args.resume) args.start_epoch = checkpoint['epoch'] model.module.load_state_dict(checkpoint['state_dict']) if not args.ft: optimizer.load_state_dict(checkpoint['optimizer']) best_pred = checkpoint['best_pred'] print("=> loaded checkpoint '{}' (epoch {})".format( args.resume, checkpoint['epoch'])) # clear start epoch if fine-tuning if args.ft: args.start_epoch = 0 # lr scheduler scheduler = utils.LR_Scheduler_Head(args.lr_scheduler, args.lr, args.epochs, len(trainloader)) def training(epoch): global best_pred train_loss = 0.0 model.train() tic = time.time() for i, (image, target) in enumerate(trainloader): scheduler(optimizer, i, epoch, best_pred) optimizer.zero_grad() outputs = model(image) target = target.cuda(args.gpu) loss = criterion(*outputs, target) loss.backward() optimizer.step() train_loss += loss.item() if i % 100 == 0 and args.gpu == 0: iter_per_sec = 100.0 / ( time.time() - tic) if i != 0 else 1.0 / (time.time() - tic) tic = time.time() print('Epoch: {}, Iter: {}, Speed: {:.3f} iter/sec, Train loss: {:.3f}'. \ format(epoch, i, iter_per_sec, train_loss / (i + 1))) def validation(epoch): # Fast test during the training using single-crop only global best_pred is_best = False model.eval() metric.reset() for i, (image, target) in enumerate(valloader): with torch.no_grad(): #correct, labeled, inter, union = eval_batch(model, image, target) pred = model(image)[0] target = target.cuda(args.gpu) metric.update(target, pred) pixAcc, mIoU = metric.get() if i % 100 == 0 and args.gpu == 0: print('pixAcc: %.3f, mIoU: %.3f' % (pixAcc, mIoU)) if args.gpu == 0: pixAcc, mIoU = torch_dist_avg(args.gpu, pixAcc, mIoU) print('pixAcc: %.3f, mIoU: %.3f' % (pixAcc, mIoU)) new_pred = (pixAcc + mIoU) / 2 if new_pred > best_pred: is_best = True best_pred = new_pred utils.save_checkpoint( { 'epoch': epoch + 1, 'state_dict': model.module.state_dict(), 'optimizer': optimizer.state_dict(), 'best_pred': best_pred, }, args, is_best) if args.gpu == 0: print('Starting Epoch:', args.start_epoch) print('Total Epoches:', args.epochs) for epoch in range(args.start_epoch, args.epochs): tic = time.time() training(epoch) if epoch % 10 == 0: validation(epoch) elapsed = time.time() - tic if args.gpu == 0: print(f'Epoch: {epoch}, Time cost: {elapsed}') validation(epoch)
def test(args): directory = "runs/val_summary/%s/%s/%s/" % (args.dataset, args.model, args.resume) if not os.path.exists(directory): os.makedirs(directory) writer = SummaryWriter(directory) # output folder outdir = 'outdir' if not os.path.exists(outdir): os.makedirs(outdir) # data transforms input_transform = transform.Compose([ transform.ToTensor(), transform.Normalize([.485, .456, .406], [.229, .224, .225]) ]) # dataset if args.eval: testset = get_segmentation_dataset(args.dataset, split='val', mode='testval', transform=input_transform) elif args.test_val: testset = get_segmentation_dataset(args.dataset, split='val', mode='test', transform=input_transform) else: testset = get_segmentation_dataset(args.dataset, split='test', mode='test', transform=input_transform) # dataloader loader_kwargs = {'num_workers': args.workers, 'pin_memory': True} \ if args.cuda else {} test_data = data.DataLoader(testset, batch_size=args.test_batch_size, drop_last=False, shuffle=False, collate_fn=test_batchify_fn, **loader_kwargs) Norm_method = torch.nn.BatchNorm2d # model if args.model_zoo is not None: model = get_model(args.model_zoo, pretrained=True) #model.base_size = args.base_size #model.crop_size = args.crop_size else: model = get_segmentation_model(args.model, dataset=args.dataset, backbone=args.backbone, aux=args.aux, multi_grid=args.multi_grid, num_center=args.num_center, norm_layer=Norm_method, root=args.backbone_path, base_size=args.base_size, crop_size=args.crop_size) # resuming checkpoint if args.resume is None or not os.path.isfile(args.resume): raise RuntimeError("=> no checkpoint found at '{}'".format( args.resume)) checkpoint = torch.load(args.resume) # strict=False, so that it is compatible with old pytorch saved models #model.module.load_state_dict(checkpoint['state_dict']) old_state_dict = checkpoint['state_dict'] new_state_dict = dict() for k, v in old_state_dict.items(): if k.startswith('module.'): #new_state_dict[k[len('module.'):]] = old_state_dict[k] new_state_dict[k[len('model.module.'):]] = old_state_dict[k] #new_state_dict[k] = old_state_dict[k] else: new_state_dict[k] = old_state_dict[k] #new_k = 'module.' + k #new_state_dict[new_k] = old_state_dict[k] model.load_state_dict(new_state_dict) print("=> loaded checkpoint '{}' (epoch {})".format( args.resume, checkpoint['epoch'])) print(model) scales = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0, 2.25] if args.dataset == 'citys' else \ [0.75, 1.0, 1.25, 1.5, 1.75, 2.0] if args.dataset == 'ade20k': scales = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0] if not args.ms: scales = [1.0] if args.dataset == 'ade20k': evaluator = MultiEvalModule2(model, testset.num_class, scales=scales, flip=args.ms).cuda() else: evaluator = MultiEvalModule(model, testset.num_class, scales=scales, flip=args.ms).cuda() evaluator.eval() metric = utils.SegmentationMetric(testset.num_class) tbar = tqdm(test_data) for i, (image, dst) in enumerate(tbar): if args.eval: with torch.no_grad(): predicts = evaluator.parallel_forward(image) metric.update(dst, predicts) pixAcc, mIoU = metric.get() tbar.set_description('pixAcc: %.4f, mIoU: %.4f' % (pixAcc, mIoU)) writer.add_scalar('pixAcc', pixAcc, i) writer.add_scalar('mIoU', mIoU, i) else: with torch.no_grad(): outputs = evaluator.parallel_forward(image) predicts = [ testset.make_pred(torch.max(output, 1)[1].cpu().numpy()) for output in outputs ] for predict, impath in zip(predicts, dst): mask = utils.get_mask_pallete(predict, args.dataset) outname = os.path.splitext(impath)[0] + '.png' mask.save(os.path.join(outdir, outname)) writer.close()
def test(args): # output folder outdir = args.save_folder if not os.path.exists(outdir): os.makedirs(outdir) # data transforms input_transform = transform.Compose([ transform.ToTensor(), transform.Normalize([.485, .456, .406], [.229, .224, .225]) ]) # dataset testset = get_segmentation_dataset(args.dataset, split=args.split, mode=args.mode, transform=input_transform) # dataloader loader_kwargs = {'num_workers': args.workers, 'pin_memory': True} \ if args.cuda else {} test_data = data.DataLoader(testset, batch_size=args.test_batch_size, drop_last=False, shuffle=False, collate_fn=test_batchify_fn, **loader_kwargs) # model if args.model_zoo is not None: model = get_model(args.model_zoo, pretrained=True) else: model = get_segmentation_model(args.model, dataset=args.dataset, backbone=args.backbone, dilated=args.dilated, multi_grid=args.multi_grid, stride=args.stride, lateral=args.lateral, jpu=args.jpu, aux=args.aux, se_loss=args.se_loss, norm_layer=BatchNorm, base_size=args.base_size, crop_size=args.crop_size) # resuming checkpoint if args.resume is None or not os.path.isfile(args.resume): raise RuntimeError("=> no checkpoint found at '{}'".format( args.resume)) checkpoint = torch.load(args.resume) # strict=False, so that it is compatible with old pytorch saved models model.load_state_dict(checkpoint['state_dict'], strict=False) print("=> loaded checkpoint '{}' (epoch {})".format( args.resume, checkpoint['epoch'])) # print(model) scales = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0, 2.25] if args.dataset == 'citys' else \ [0.5, 0.75, 1.0, 1.25, 1.5, 1.75] if not args.ms: scales = [1.0] evaluator = MultiEvalModule(model, testset.num_class, scales=scales, flip=args.ms).cuda() evaluator.eval() metric = utils.SegmentationMetric(testset.num_class) tbar = tqdm(test_data) total_inter, total_union, total_correct, total_label, all_label = 0, 0, 0, 0, 0 # for i, (image, dst) in enumerate(tbar): # # print(dst) # with torch.no_grad(): # outputs = evaluator.parallel_forward(image)[0] # correct, labeled = batch_pix_accuracy(outputs, dst[0]) # total_correct += correct # all_label += labeled # img_pixAcc = 1.0 * correct / (np.spacing(1) + labeled) # inter, union, area_pred, area_lab = batch_intersection_union(outputs, dst[0], testset.num_class) # total_label += area_lab # total_inter += inter # total_union += union # class_pixAcc = 1.0 * inter / (np.spacing(1) + area_lab) # class_IoU = 1.0 * inter / (np.spacing(1) + union) # class_mIoU = class_IoU.mean() # print("img pixAcc:", img_pixAcc) # print("img Classes pixAcc:", class_pixAcc) # print("img Classes IoU:", class_IoU) # total_pixAcc = 1.0 * total_correct / (np.spacing(1) + all_label) # pixAcc = 1.0 * total_inter / (np.spacing(1) + total_label) # IoU = 1.0 * total_inter / (np.spacing(1) + total_union) # mIoU = IoU.mean() # print("set pixAcc:", pixAcc) # print("set Classes pixAcc:", pixAcc) # print("set Classes IoU:", IoU) # print("set mean IoU:", mIoU) for i, (image, dst) in enumerate(tbar): if 'val' in args.mode: with torch.no_grad(): predicts = evaluator.parallel_forward(image) # metric.update(dst[0], predicts[0]) # pixAcc, mIoU = metric.get() # tbar.set_description( 'pixAcc: %.4f, mIoU: %.4f' % (pixAcc, mIoU)) else: with torch.no_grad(): outputs = evaluator.parallel_forward(image)
trainloader = data.DataLoader(ReturnFirstClosure(trainset), batch_size=args.batch_size, drop_last=True, shuffle=True, **loader_kwargs) print('Reseting BN statistics') #model.apply(reset_bn_statistics) model.cuda() update_bn_stats(model, trainloader) if args.export: torch.save(model.state_dict(), args.export + '.pth') return scales = [0.75, 1.0, 1.25, 1.5, 1.75, 2.0, 2.25] if args.dataset == 'citys' else \ [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]#, 2.0 evaluator = MultiEvalModule(model, testset.num_class, scales=scales).cuda() evaluator.eval() metric = utils.SegmentationMetric(testset.num_class) tbar = tqdm(test_data) for i, (image, dst) in enumerate(tbar): if args.eval: with torch.no_grad(): predicts = evaluator.parallel_forward(image) metric.update(dst, predicts) pixAcc, mIoU = metric.get() tbar.set_description( 'pixAcc: %.4f, mIoU: %.4f' % (pixAcc, mIoU)) else: with torch.no_grad(): outputs = evaluator.parallel_forward(image) predicts = [testset.make_pred(torch.max(output, 1)[1].cpu().numpy()) for output in outputs] for predict, impath in zip(predicts, dst):