def test_revert_sync_batchnorm(): conv_syncbn = ConvModule(3, 8, 2, norm_cfg=dict(type='SyncBN')).to('cpu') conv_syncbn.train() x = torch.randn(1, 3, 10, 10) # Will raise an ValueError saying SyncBN does not run on CPU with pytest.raises(ValueError): y = conv_syncbn(x) conv_bn = revert_sync_batchnorm(conv_syncbn) y = conv_bn(x) assert y.shape == (1, 8, 9, 9) assert conv_bn.training == conv_syncbn.training conv_syncbn.eval() conv_bn = revert_sync_batchnorm(conv_syncbn) assert conv_bn.training == conv_syncbn.training
def test_psenet(cfg_file): model = _get_detector_cfg(cfg_file) model['pretrained'] = None from mmocr.models import build_detector detector = build_detector(model) detector = revert_sync_batchnorm(detector) input_shape = (1, 3, 224, 224) num_kernels = 7 mm_inputs = _demo_mm_inputs(num_kernels, input_shape) imgs = mm_inputs.pop('imgs') img_metas = mm_inputs.pop('img_metas') gt_kernels = mm_inputs.pop('gt_kernels') gt_mask = mm_inputs.pop('gt_mask') # Test forward train losses = detector.forward( imgs, img_metas, gt_kernels=gt_kernels, gt_mask=gt_mask) assert isinstance(losses, dict) # Test forward test with torch.no_grad(): img_list = [g[None, :] for g in imgs] batch_results = [] for one_img, one_meta in zip(img_list, img_metas): result = detector.forward([one_img], [[one_meta]], return_loss=False) batch_results.append(result) # Test show result results = {'boundary_result': [[0, 0, 1, 0, 1, 1, 0, 1, 0.9]]} img = np.random.rand(5, 5) detector.show_result(img, results)
def build_model(config_file): device = 'cpu' model = init_detector(config_file, checkpoint=None, device=device) model = revert_sync_batchnorm(model) if model.cfg.data.test['type'] == 'ConcatDataset': model.cfg.data.test.pipeline = model.cfg.data.test['datasets'][ 0].pipeline return model
def test_fcenet(cfg_file): model = _get_detector_cfg(cfg_file) model['pretrained'] = None from mmocr.models import build_detector detector = build_detector(model) detector = revert_sync_batchnorm(detector) detector = detector.cuda() fourier_degree = 5 input_shape = (1, 3, 256, 256) (n, c, h, w) = input_shape imgs = torch.randn(n, c, h, w).float().cuda() img_metas = [{ 'img_shape': (h, w, c), 'ori_shape': (h, w, c), 'pad_shape': (h, w, c), 'filename': '<demo>.png', 'scale_factor': np.array([1, 1, 1, 1]), 'flip': False, } for _ in range(n)] p3_maps = [] p4_maps = [] p5_maps = [] for _ in range(n): p3_maps.append( np.random.random((5 + 4 * fourier_degree, h // 8, w // 8))) p4_maps.append( np.random.random((5 + 4 * fourier_degree, h // 16, w // 16))) p5_maps.append( np.random.random((5 + 4 * fourier_degree, h // 32, w // 32))) # Test forward train losses = detector.forward(imgs, img_metas, p3_maps=p3_maps, p4_maps=p4_maps, p5_maps=p5_maps) assert isinstance(losses, dict) # Test forward test with torch.no_grad(): img_list = [g[None, :] for g in imgs] batch_results = [] for one_img, one_meta in zip(img_list, img_metas): result = detector.forward([one_img], [[one_meta]], return_loss=False) batch_results.append(result) # Test show result results = {'boundary_result': [[0, 0, 1, 0, 1, 1, 0, 1, 0.9]]} img = np.random.rand(5, 5) detector.show_result(img, results)
def test_textsnake(cfg_file): model = _get_detector_cfg(cfg_file) model['pretrained'] = None from mmocr.models import build_detector detector = build_detector(model) detector = revert_sync_batchnorm(detector) input_shape = (1, 3, 224, 224) num_kernels = 1 mm_inputs = _demo_mm_inputs(num_kernels, input_shape) imgs = mm_inputs.pop('imgs') img_metas = mm_inputs.pop('img_metas') gt_text_mask = mm_inputs.pop('gt_text_mask') gt_center_region_mask = mm_inputs.pop('gt_center_region_mask') gt_mask = mm_inputs.pop('gt_mask') gt_radius_map = mm_inputs.pop('gt_radius_map') gt_sin_map = mm_inputs.pop('gt_sin_map') gt_cos_map = mm_inputs.pop('gt_cos_map') # Test forward train losses = detector.forward( imgs, img_metas, gt_text_mask=gt_text_mask, gt_center_region_mask=gt_center_region_mask, gt_mask=gt_mask, gt_radius_map=gt_radius_map, gt_sin_map=gt_sin_map, gt_cos_map=gt_cos_map) assert isinstance(losses, dict) # Test forward test get_boundary maps = torch.zeros((1, 5, 224, 224), dtype=torch.float) maps[:, 0:2, :, :] = -10. maps[:, 0, 60:100, 12:212] = 10. maps[:, 1, 70:90, 22:202] = 10. maps[:, 2, 70:90, 22:202] = 0. maps[:, 3, 70:90, 22:202] = 1. maps[:, 4, 70:90, 22:202] = 10. one_meta = img_metas[0] result = detector.bbox_head.get_boundary(maps, [one_meta], False) assert 'boundary_result' in result assert 'filename' in result # Test show result results = {'boundary_result': [[0, 0, 1, 0, 1, 1, 0, 1, 0.9]]} img = np.random.rand(5, 5) detector.show_result(img, results)
def test_panet(cfg_file): model = _get_detector_cfg(cfg_file) model['pretrained'] = None from mmocr.models import build_detector detector = build_detector(model) detector = revert_sync_batchnorm(detector) input_shape = (1, 3, 224, 224) num_kernels = 2 mm_inputs = _demo_mm_inputs(num_kernels, input_shape) imgs = mm_inputs.pop('imgs') img_metas = mm_inputs.pop('img_metas') gt_kernels = mm_inputs.pop('gt_kernels') gt_mask = mm_inputs.pop('gt_mask') # Test forward train losses = detector.forward(imgs, img_metas, gt_kernels=gt_kernels, gt_mask=gt_mask) assert isinstance(losses, dict) # Test forward test with torch.no_grad(): img_list = [g[None, :] for g in imgs] batch_results = [] for one_img, one_meta in zip(img_list, img_metas): result = detector.forward([one_img], [[one_meta]], return_loss=False) batch_results.append(result) # Test onnx export detector.forward = partial(detector.simple_test, img_metas=img_metas, rescale=True) with tempfile.TemporaryDirectory() as tmpdirname: onnx_path = f'{tmpdirname}/tmp.onnx' torch.onnx.export(detector, (img_list[0], ), onnx_path, input_names=['input'], output_names=['output'], export_params=True, keep_initializers_as_inputs=False) # Test show result results = {'boundary_result': [[0, 0, 1, 0, 1, 1, 0, 1, 0.9]]} img = np.random.rand(5, 5) detector.show_result(img, results)
def main(): args = parse_args() assert ( args.out or args.eval or args.format_only or args.show or args.show_dir), ( 'Please specify at least one operation (save/eval/format/show the ' 'results / save the results) with the argument "--out", "--eval"' ', "--format-only", "--show" or "--show-dir".') if args.eval and args.format_only: raise ValueError('--eval and --format_only cannot be both specified.') if args.out is not None and not args.out.endswith(('.pkl', '.pickle')): raise ValueError('The output file must be a pkl file.') cfg = Config.fromfile(args.config) if args.cfg_options is not None: cfg.merge_from_dict(args.cfg_options) # import modules from string list. if cfg.get('custom_imports', None): from mmcv.utils import import_modules_from_strings import_modules_from_strings(**cfg['custom_imports']) # set cudnn_benchmark if cfg.get('cudnn_benchmark', False): torch.backends.cudnn.benchmark = True if cfg.model.get('pretrained'): cfg.model.pretrained = None if cfg.model.get('neck'): if isinstance(cfg.model.neck, list): for neck_cfg in cfg.model.neck: if neck_cfg.get('rfp_backbone'): if neck_cfg.rfp_backbone.get('pretrained'): neck_cfg.rfp_backbone.pretrained = None elif cfg.model.neck.get('rfp_backbone'): if cfg.model.neck.rfp_backbone.get('pretrained'): cfg.model.neck.rfp_backbone.pretrained = None # in case the test dataset is concatenated samples_per_gpu = 1 if isinstance(cfg.data.test, dict): samples_per_gpu = (cfg.data.get('test_dataloader', {})).get( 'samples_per_gpu', cfg.data.get('samples_per_gpu', 1)) if samples_per_gpu > 1: # Support batch_size > 1 in test for text recognition # by disable MultiRotateAugOCR since it is useless for most case cfg = disable_text_recog_aug_test(cfg) if cfg.data.test.get('pipeline', None) is not None: # Replace 'ImageToTensor' to 'DefaultFormatBundle' cfg.data.test.pipeline = replace_ImageToTensor( cfg.data.test.pipeline) elif isinstance(cfg.data.test, list): for ds_cfg in cfg.data.test: ds_cfg.test_mode = True samples_per_gpu = max( [ds_cfg.pop('samples_per_gpu', 1) for ds_cfg in cfg.data.test]) if samples_per_gpu > 1: for ds_cfg in cfg.data.test: ds_cfg.pipeline = replace_ImageToTensor(ds_cfg.pipeline) # init distributed env first, since logger depends on the dist info. if args.launcher == 'none': distributed = False else: distributed = True init_dist(args.launcher, **cfg.dist_params) # build the dataloader dataset = build_dataset(cfg.data.test, dict(test_mode=True)) # step 1: give default values and override (if exist) from cfg.data loader_cfg = { **dict(seed=cfg.get('seed'), drop_last=False, dist=distributed), **({} if torch.__version__ != 'parrots' else dict( prefetch_num=2, pin_memory=False, )), **dict((k, cfg.data[k]) for k in [ 'workers_per_gpu', 'seed', 'prefetch_num', 'pin_memory', 'persistent_workers', ] if k in cfg.data) } test_loader_cfg = { **loader_cfg, **dict(shuffle=False, drop_last=False), **cfg.data.get('test_dataloader', {}), **dict(samples_per_gpu=samples_per_gpu) } data_loader = build_dataloader(dataset, **test_loader_cfg) # build the model and load checkpoint cfg.model.train_cfg = None model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg')) model = revert_sync_batchnorm(model) fp16_cfg = cfg.get('fp16', None) if fp16_cfg is not None: wrap_fp16_model(model) load_checkpoint(model, args.checkpoint, map_location='cpu') if args.fuse_conv_bn: model = fuse_conv_bn(model) if not distributed: model = MMDataParallel(model, device_ids=[0]) is_kie = cfg.model.type in ['SDMGR'] outputs = single_gpu_test(model, data_loader, args.show, args.show_dir, is_kie, args.show_score_thr) else: model = MMDistributedDataParallel( model.cuda(), device_ids=[torch.cuda.current_device()], broadcast_buffers=False) outputs = multi_gpu_test(model, data_loader, args.tmpdir, args.gpu_collect) rank, _ = get_dist_info() if rank == 0: if args.out: print(f'\nwriting results to {args.out}') mmcv.dump(outputs, args.out) kwargs = {} if args.eval_options is None else args.eval_options if args.format_only: dataset.format_results(outputs, **kwargs) if args.eval: eval_kwargs = cfg.get('evaluation', {}).copy() # hard-code way to remove EvalHook args for key in [ 'interval', 'tmpdir', 'start', 'gpu_collect', 'save_best', 'rule' ]: eval_kwargs.pop(key, None) eval_kwargs.update(dict(metric=args.eval, **kwargs)) print(dataset.evaluate(outputs, **eval_kwargs))
def test_drrg(cfg_file): model = _get_detector_cfg(cfg_file) model['pretrained'] = None from mmocr.models import build_detector detector = build_detector(model) detector = revert_sync_batchnorm(detector) input_shape = (1, 3, 224, 224) num_kernels = 1 mm_inputs = _demo_mm_inputs(num_kernels, input_shape) imgs = mm_inputs.pop('imgs') img_metas = mm_inputs.pop('img_metas') gt_text_mask = mm_inputs.pop('gt_text_mask') gt_center_region_mask = mm_inputs.pop('gt_center_region_mask') gt_mask = mm_inputs.pop('gt_mask') gt_top_height_map = mm_inputs.pop('gt_radius_map') gt_bot_height_map = gt_top_height_map.copy() gt_sin_map = mm_inputs.pop('gt_sin_map') gt_cos_map = mm_inputs.pop('gt_cos_map') num_rois = 32 x = np.random.randint(4, 224, (num_rois, 1)) y = np.random.randint(4, 224, (num_rois, 1)) h = 4 * np.ones((num_rois, 1)) w = 4 * np.ones((num_rois, 1)) angle = (np.random.random_sample((num_rois, 1)) * 2 - 1) * np.pi / 2 cos, sin = np.cos(angle), np.sin(angle) comp_labels = np.random.randint(1, 3, (num_rois, 1)) num_rois = num_rois * np.ones((num_rois, 1)) comp_attribs = np.hstack([num_rois, x, y, h, w, cos, sin, comp_labels]) gt_comp_attribs = np.expand_dims(comp_attribs.astype(np.float32), axis=0) # Test forward train losses = detector.forward( imgs, img_metas, gt_text_mask=gt_text_mask, gt_center_region_mask=gt_center_region_mask, gt_mask=gt_mask, gt_top_height_map=gt_top_height_map, gt_bot_height_map=gt_bot_height_map, gt_sin_map=gt_sin_map, gt_cos_map=gt_cos_map, gt_comp_attribs=gt_comp_attribs) assert isinstance(losses, dict) # Test forward test model['bbox_head']['in_channels'] = 6 model['bbox_head']['text_region_thr'] = 0.8 model['bbox_head']['center_region_thr'] = 0.8 detector = build_detector(model) maps = torch.zeros((1, 6, 224, 224), dtype=torch.float) maps[:, 0:2, :, :] = -10. maps[:, 0, 60:100, 50:170] = 10. maps[:, 1, 75:85, 60:160] = 10. maps[:, 2, 75:85, 60:160] = 0. maps[:, 3, 75:85, 60:160] = 1. maps[:, 4, 75:85, 60:160] = 10. maps[:, 5, 75:85, 60:160] = 10. with torch.no_grad(): full_pass_weight = torch.zeros((6, 6, 1, 1)) for i in range(6): full_pass_weight[i, i, 0, 0] = 1 detector.bbox_head.out_conv.weight.data = full_pass_weight detector.bbox_head.out_conv.bias.data.fill_(0.) outs = detector.bbox_head.single_test(maps) boundaries = detector.bbox_head.get_boundary(*outs, img_metas, True) assert len(boundaries) == 1 # Test show result results = {'boundary_result': [[0, 0, 1, 0, 1, 1, 0, 1, 0.9]]} img = np.random.rand(5, 5) detector.show_result(img, results)
def build_model(config_file): device = 'cpu' model = init_detector(config_file, checkpoint=None, device=device) model = revert_sync_batchnorm(model) return model
def build_model(cfg): model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg')) model = revert_sync_batchnorm(model) model = MMDataParallel(model) return model