def load_data(args): """ Modify this to load your data and labels """ validation_data_params = { "dim": (args.patch_dim, args.patch_dim, args.patch_dim), "batch_size": 1, "n_in_channels": args.number_input_channels, "n_out_channels": 1, "train_test_split": args.train_test_split, "augment": False, "shuffle": False, "seed": args.random_seed } validation_generator = DataGenerator(False, args.data_path, **validation_data_params) # for batch_idx in tqdm(range(validation_generator.num_batches), # desc="Predicting on batch"): batch_idx = 0 imgs, msks = validation_generator.get_batch(batch_idx) fileIDs = validation_generator.get_batch_fileIDs(batch_idx) """ OpenVINO uses channels first tensors (NCHWD). TensorFlow usually does channels last (NHWDC). So we need to transpose the axes. """ imgs = imgs.transpose((0, 4, 1, 2, 3)) msks = msks.transpose((0, 4, 1, 2, 3)) return imgs, msks, fileIDs
print("{} = {:.4f}".format(name, m[i])) i += 1 save_directory = "predictions_directory" try: os.stat(save_directory) except: os.mkdir(save_directory) print("Predicting masks") for batch_idx in tqdm(range(validation_generator.num_batches), desc="Predicting on batch"): imgs, msks = validation_generator.get_batch(batch_idx) fileIDs = validation_generator.get_batch_fileIDs(batch_idx) preds = model.predict_on_batch(imgs) # Save the predictions as Nifti files so that we can # display them on a 3D viewer. for idx in tqdm(range(preds.shape[0]), desc="Saving to Nifti file"): img = nib.Nifti1Image(imgs[idx, :, :, :, 0], np.eye(4)) img.to_filename( os.path.join(save_directory, "{}_img.nii.gz".format(fileIDs[idx]))) msk = nib.Nifti1Image(msks[idx, :, :, :, 0], np.eye(4)) msk.to_filename( os.path.join(save_directory, "{}_msk.nii.gz".format(fileIDs[idx])))
print("{} = {:.4f}".format(name, m[idx])) save_directory = "predictions_directory" try: os.stat(save_directory) except: os.mkdir(save_directory) print("Predicting masks") for batch_idx in tqdm(range(testing_generator.num_batches), desc="Predicting on batch"): imgs, msks = testing_generator.get_batch(batch_idx) fileIDs = testing_generator.get_batch_fileIDs(batch_idx) preds = model.predict_on_batch(imgs) # Save the predictions as Nifti files so that we can # display them on a 3D viewer. for idx in tqdm(range(preds.shape[0]), desc="Saving to Nifti file"): img = nib.Nifti1Image(imgs[idx, :, :, :, 0], np.eye(4)) img.to_filename(os.path.join(save_directory, "{}_img.nii.gz".format(fileIDs[idx]))) msk = nib.Nifti1Image(msks[idx, :, :, :, 0], np.eye(4)) msk.to_filename(os.path.join(save_directory, "{}_msk.nii.gz".format(fileIDs[idx])))