def __getitem__(self, index): image = read_image(self.file_paths[index]) if len(image.shape) < 3: image = image[..., np.newaxis] image = torch.Tensor(image.transpose(2, 0, 1)) if self.has_target: return image, self.target[index] return image
def _image_to_array(img_path): """Read the image from the path and return image object. Return an image object. Args: img_path: image file name in images_dir_path. """ if os.path.exists(img_path): img = read_image(img_path) if len(img.shape) < 3: img = img[..., np.newaxis] return img else: raise ValueError("%s image does not exist" % img_path)
def _image_to_array(img_path): """Read the image from the path and return it as an numpy.ndarray. Load the image file as an array Args: img_path: a string whose value is the image file name """ if os.path.exists(img_path): img = read_image(img_path) if len(img.shape) < 3: img = img[..., np.newaxis] return img else: raise ValueError("%s image does not exist" % img_path)
def read_images(img_file_names, images_dir_path): """Read the images from the path and return their numpy.ndarray instance. Return a numpy.ndarray instance containing the training data. Args: img_file_names: List containing images names. images_dir_path: Path to the directory containing images. """ x_train = [] if os.path.isdir(images_dir_path): for img_file in img_file_names: img_path = os.path.join(images_dir_path, img_file) if os.path.exists(img_path): img = read_image(img_path) if len(img.shape) < 3: img = img[..., np.newaxis] x_train.append(img) else: raise ValueError("%s image does not exist" % img_file) else: raise ValueError("Directory containing images does not exist") return np.asanyarray(x_train)