def abstract_test_single_dataset_raw_gt_with_val(in_memory): # Dataset 1 has 4 raw images and 2 gt images dataset_1_raw = conftest.dataset_1_raw_images() dataset_1_gt = conftest.dataset_1_gt_images() factor = 2 dataset = TrainingDataset([conftest.dataset_1_raw_dir.name], [conftest.dataset_1_gt_dir.name], batch_size=2, val_ratio=0.5, add_normalization_transform=False, keep_in_memory=in_memory) TrainingDataset._dataset_index_proportional = _dataset_index_proportional_single_dataset assert len(dataset) == 4 # indices[0] because we only have one dataset assert len(dataset.train_indices[0]) == 2 assert len(dataset.val_indices[0]) == 2 # We get back a batch of size 4 with all images in order sample = next(iter(dataset)) for i, raw in enumerate(sample['raw']): mask = sample['mask'][i].astype(np.bool) assert mask.all() # Second half are training indices in TrainingDataset assert np.array_equal(raw, dataset_1_raw[i + 2]) assert np.array_equal(sample['gt'][i], dataset_1_gt[int( (i + 2) / factor)]) for val in dataset.validation_samples(): for i, raw in enumerate(val['raw']): val_raw = raw.squeeze() val_gt = val['gt'][i].squeeze() mask = val['mask'][i].squeeze().astype(np.bool) assert mask.all() assert np.array_equal(val_raw, dataset_1_raw[i]) assert np.array_equal(val_gt, dataset_1_gt[int(i / factor)])
def test_single_dataset_gt_images(): dataset = PredictionDataset([conftest.dataset_1_raw_dir.name], [conftest.dataset_1_gt_dir.name]) assert len(dataset) == 4 raw_images = np.array(conftest.dataset_1_raw_images()) gt_images = np.array(conftest.dataset_1_gt_images()) factor = int(len(raw_images) / len(gt_images)) for i, dataset_image in enumerate(dataset): raw_image = dataset_image['raw'] gt_image = dataset_image['gt'] assert np.array_equal(raw_image, raw_images[i]) assert np.array_equal(gt_image, gt_images[int(i / factor)])
def abstract_test_multi_dataset_raw_gt(in_memory): # Dataset 1 has 4 raw images and 2 gt images raw_datasets = [ conftest.dataset_1_raw_images(), conftest.dataset_2_raw_images(), conftest.dataset_3_raw_images() ] gt_datasets = [ conftest.dataset_1_gt_images(), conftest.dataset_2_gt_images(), conftest.dataset_3_gt_images() ] dataset = TrainingDataset([ conftest.dataset_1_raw_dir.name, conftest.dataset_2_raw_dir.name, conftest.dataset_3_raw_dir.name ], [ conftest.dataset_1_gt_dir.name, conftest.dataset_2_gt_dir.name, conftest.dataset_3_gt_dir.name ], batch_size=9, val_ratio=0, add_normalization_transform=False, keep_in_memory=in_memory) IndexProportionalGenerator.counter = 0 TrainingDataset._dataset_index_proportional =\ IndexProportionalGenerator.index_without_val # indices[0] because we only have one dataset assert len(dataset) == 9 assert len([idx for sub in dataset.train_indices for idx in sub]) == 9 assert len([idx for sub in dataset.val_indices for idx in sub]) == 0 dataset_indices = [0, 0, 0, 0, 1, 1, 2, 2, 2] raw_indices = [0, 1, 2, 3, 0, 1, 0, 1, 2] gt_indices = [0, 0, 1, 1, 0, 1, 0, 0, 0] # We get back a batch of size 4 with all images in order sample = next(iter(dataset)) for i, raw in enumerate(sample['raw']): mask = sample['mask'][i].astype(np.bool) assert mask.all() gt = sample['gt'][i] dataset_index = dataset_indices[i] raw_index = raw_indices[i] gt_index = gt_indices[i] # Second half are training indices in TrainingDataset raw_dataset = raw_datasets[dataset_index] gt_dataset = gt_datasets[dataset_index] assert np.array_equal(raw, raw_dataset[raw_index]) assert np.array_equal(gt, gt_dataset[gt_index])
def test_multi_dataset_gt_images(): dataset = PredictionDataset([ conftest.dataset_1_raw_dir.name, conftest.dataset_2_raw_dir.name, conftest.dataset_3_raw_dir.name ], [ conftest.dataset_1_gt_dir.name, conftest.dataset_2_gt_dir.name, conftest.dataset_3_gt_dir.name ]) raw = conftest.dataset_1_raw_images() raw2 = conftest.dataset_2_raw_images() raw3 = conftest.dataset_3_raw_images() gt = conftest.dataset_1_gt_images() gt2 = conftest.dataset_2_gt_images() gt3 = conftest.dataset_3_gt_images() factors = [ int(len(raw) / len(gt)), int(len(raw2) / len(gt2)), int(len(raw3) / len(gt3)) ] raw.extend(raw2) raw.extend(raw3) raw = np.array(raw) for i, sample in enumerate(dataset): if i < 4: factor = factors[0] current_gt = gt gt_idx = i elif i < 6: factor = factors[1] current_gt = gt2 # because first dataset has 4 entries gt_idx = i - 4 else: factor = factors[2] current_gt = gt3 # because second dataset has an additional 2 entries gt_idx = i - 6 raw_ = sample['raw'] gt_ = sample['gt'] assert np.array_equal(raw[i], raw_) assert np.array_equal(current_gt[int(gt_idx / factor)], gt_)
def abstract_test_multi_dataset_raw_gt_with_val_even(in_memory): # Dataset 1 has 4 raw images and 2 gt images raw_datasets = [ conftest.dataset_1_raw_images(), conftest.dataset_2_raw_images(), conftest.dataset_3_raw_images() ] gt_datasets = [ conftest.dataset_1_gt_images(), conftest.dataset_2_gt_images(), conftest.dataset_3_gt_images() ] dataset = TrainingDataset([ conftest.dataset_1_raw_dir.name, conftest.dataset_2_raw_dir.name, conftest.dataset_3_raw_dir.name ], [ conftest.dataset_1_gt_dir.name, conftest.dataset_2_gt_dir.name, conftest.dataset_3_gt_dir.name ], batch_size=6, val_ratio=0.5, add_normalization_transform=False, keep_in_memory=in_memory) IndexEvenGenerator.counter = 0 TrainingDataset._dataset_index_proportional = IndexEvenGenerator.index # Order of indices because we cut off a part for validation # dataset 0 1 2 0 1 2 raw_indices = [2, 1, 1, 3, 1, 2] gt_indices = [1, 1, 0, 1, 1, 0] # indices[0] because we only have one dataset assert len(dataset) == 9 assert len([idx for sub in dataset.train_indices for idx in sub]) == 5 assert len([idx for sub in dataset.val_indices for idx in sub]) == 4 # We get back a batch of size 4 with all images in order sample = next(iter(dataset)) for i, raw in enumerate(sample['raw']): mask = sample['mask'][i].astype(np.bool) assert mask.all() gt = sample['gt'][i] # We are looping through the datasets evenly dataset_index = i % 3 raw_dataset = raw_datasets[dataset_index] gt_dataset = gt_datasets[dataset_index] raw_index = raw_indices[i] gt_index = gt_indices[i] assert np.array_equal(raw, raw_dataset[raw_index]) assert np.array_equal(gt, gt_dataset[gt_index]) # datasets 0 1 2 0 val_raw_indices = [0, 0, 0, 1] val_gt_indices = [0, 0, 0, 0] for i, val in enumerate(dataset.validation_samples()): mask = val['mask'][i].astype(np.bool) assert mask.all() gt = val['gt'][i] # We are looping through the datasets evenly dataset_index = i % 3 raw_dataset = raw_datasets[dataset_index] raw_index = val_raw_indices[i] raw = raw_dataset[raw_index] gt_dataset = gt_datasets[dataset_index] gt_index = val_gt_indices[i] gt = gt_dataset[gt_index] assert np.array_equal(raw, raw_dataset[raw_index]) assert np.array_equal(gt, gt_dataset[gt_index])