def _get_batches_of_transformed_samples(self, index_array): V_red = self.image_data_generator.V_red batch_x = np.zeros( (len(index_array), V_red.shape[1]), dtype=self.dtype ) #tuple([len(index_array)] + list(self.x.shape)[1:]), # dtype=self.dtype) for i, j in enumerate(index_array): x = self.x[j] params = self.image_data_generator.get_random_transform(x.shape) x = self.image_data_generator.apply_transform( x.astype(self.dtype), params) # x = self.image_data_generator.standardize(x) batch_x[i] = np.dot(np.reshape(x, (1, 2916)), V_red) if self.save_to_dir: for i, j in enumerate(index_array): img = array_to_img(batch_x[i], self.data_format, scale=True) fname = '{prefix}_{index}_{hash}.{format}'.format( prefix=self.save_prefix, index=j, hash=np.random.randint(1e4), format=self.save_format) img.save(os.path.join(self.save_to_dir, fname)) batch_x_miscs = [xx[index_array] for xx in self.x_misc] output = (batch_x if batch_x_miscs == [] else [batch_x] + batch_x_miscs, ) if self.y is None: return output[0] output += (self.y[index_array], ) if self.sample_weight is not None: output += (self.sample_weight[index_array], ) return output
def _get_batches_of_transformed_samples(self, index_array): # build batch of image data batch_x = np.array([self.x[j] for j in index_array]) # transform the image data batch_x = np.array( [self.image_data_generator.transform_image(x) for x in batch_x]) if self.y is not None: batch_y = np.array([self.y[j] for j in index_array]) else: batch_y = np.array([]) if self.save_to_dir: for i, j in enumerate(index_array): img = array_to_img(batch_x[i], self.data_format, scale=True) fname = '{prefix}_{index}_{hash}.{format}'.format( prefix=self.save_prefix, index=j, hash=np.random.randint(1e4), format=self.save_format) img.save(os.path.join(self.save_to_dir, fname)) batch_x_miscs = [xx[index_array] for xx in self.x_misc] output = (batch_x if batch_x_miscs == [] else [batch_x] + batch_x_miscs, ) if self.y is None: return output[0] output += (batch_y, ) if self.sample_weight is not None: output += (self.sample_weight[index_array], ) return output
def _get_batches_of_transformed_samples(self, index_array): """Gets a batch of transformed samples. # Arguments index_array: Array of sample indices to include in batch. # Returns A batch of transformed samples. """ # build batch of image data # self.filepaths is dynamic, is better to call it once outside the loop filepaths = self.filepaths # build batch of image data batch_x = np.array([ load_img(filepaths[x], color_mode=self.color_mode, target_size=self.target_size, interpolation=self.interpolation) for x in index_array ]) # transform the image data batch_x = np.array( [self.image_data_generator.transform_image(x) for x in batch_x]) # optionally save augmented images to disk for debugging purposes if self.save_to_dir: for i, j in enumerate(index_array): img = array_to_img(batch_x[i], self.data_format, scale=True) fname = '{prefix}_{index}_{hash}.{format}'.format( prefix=self.save_prefix, index=j, hash=np.random.randint(1e7), format=self.save_format) img.save(os.path.join(self.save_to_dir, fname)) # build batch of labels if self.class_mode == 'input': batch_y = batch_x.copy() elif self.class_mode in {'binary', 'sparse'}: batch_y = np.empty(len(batch_x), dtype=self.dtype) for i, n_observation in enumerate(index_array): batch_y[i] = self.classes[n_observation] elif self.class_mode == 'categorical': batch_y = np.zeros((len(batch_x), len(self.class_indices)), dtype=self.dtype) for i, n_observation in enumerate(index_array): batch_y[i, self.classes[n_observation]] = 1. elif self.class_mode == 'multi_output': batch_y = [output[index_array] for output in self.labels] elif self.class_mode == 'raw': batch_y = self.labels[index_array] else: return batch_x if self.sample_weight is None: return batch_x, batch_y else: return batch_x, batch_y, self.sample_weight[index_array]
def test_array_to_img_and_img_to_array(): height, width = 10, 8 # Test the data format # Test RGB 3D x = np.random.random((3, height, width)) img = utils.array_to_img(x, data_format='channels_first') assert img.size == (width, height) x = utils.img_to_array(img, data_format='channels_first') assert x.shape == (3, height, width) # Test RGBA 3D x = np.random.random((4, height, width)) img = utils.array_to_img(x, data_format='channels_first') assert img.size == (width, height) x = utils.img_to_array(img, data_format='channels_first') assert x.shape == (4, height, width) # Test 2D x = np.random.random((1, height, width)) img = utils.array_to_img(x, data_format='channels_first') assert img.size == (width, height) x = utils.img_to_array(img, data_format='channels_first') assert x.shape == (1, height, width) # grayscale 32-bit signed integer x = np.array( np.random.randint(-2147483648, 2147483647, (1, height, width)), dtype=np.int32 ) img = utils.array_to_img(x, data_format='channels_first') assert img.size == (width, height) x = utils.img_to_array(img, data_format='channels_first') assert x.shape == (1, height, width) # Test tf data format # Test RGB 3D x = np.random.random((height, width, 3)) img = utils.array_to_img(x, data_format='channels_last') assert img.size == (width, height) x = utils.img_to_array(img, data_format='channels_last') assert x.shape == (height, width, 3) # Test RGBA 3D x = np.random.random((height, width, 4)) img = utils.array_to_img(x, data_format='channels_last') assert img.size == (width, height) x = utils.img_to_array(img, data_format='channels_last') assert x.shape == (height, width, 4) # Test 2D x = np.random.random((height, width, 1)) img = utils.array_to_img(x, data_format='channels_last') assert img.size == (width, height) x = utils.img_to_array(img, data_format='channels_last') assert x.shape == (height, width, 1) # grayscale 16-bit signed integer x = np.array( np.random.randint(-2147483648, 2147483647, (height, width, 1)), dtype=np.int16 ) img = utils.array_to_img(x, data_format='channels_last') assert img.size == (width, height) x = utils.img_to_array(img, data_format='channels_last') assert x.shape == (height, width, 1) # grayscale 32-bit signed integer x = np.array( np.random.randint(-2147483648, 2147483647, (height, width, 1)), dtype=np.int32 ) img = utils.array_to_img(x, data_format='channels_last') assert img.size == (width, height) x = utils.img_to_array(img, data_format='channels_last') assert x.shape == (height, width, 1) # Test invalid use case with pytest.raises(ValueError): x = np.random.random((height, width)) # not 3D img = utils.array_to_img(x, data_format='channels_first') with pytest.raises(ValueError): x = np.random.random((height, width, 3)) # unknown data_format img = utils.array_to_img(x, data_format='channels') with pytest.raises(ValueError): # neither RGB, RGBA, or gray-scale x = np.random.random((height, width, 5)) img = utils.array_to_img(x, data_format='channels_last') with pytest.raises(ValueError): x = np.random.random((height, width, 3)) # unknown data_format img = utils.img_to_array(x, data_format='channels') with pytest.raises(ValueError): # neither RGB, RGBA, or gray-scale x = np.random.random((height, width, 5, 3)) img = utils.img_to_array(x, data_format='channels_last')
def test_load_img(tmpdir): filename_rgb = str(tmpdir / 'rgb_utils.png') filename_rgba = str(tmpdir / 'rgba_utils.png') filename_grayscale_8bit = str(tmpdir / 'grayscale_8bit_utils.png') filename_grayscale_16bit = str(tmpdir / 'grayscale_16bit_utils.tiff') filename_grayscale_32bit = str(tmpdir / 'grayscale_32bit_utils.tiff') original_rgb_array = np.array(255 * np.random.rand(100, 100, 3), dtype=np.uint8) original_rgb = utils.array_to_img(original_rgb_array, scale=False) original_rgb.save(filename_rgb) original_rgba_array = np.array(255 * np.random.rand(100, 100, 4), dtype=np.uint8) original_rgba = utils.array_to_img(original_rgba_array, scale=False) original_rgba.save(filename_rgba) original_grayscale_8bit_array = np.array(255 * np.random.rand(100, 100, 1), dtype=np.uint8) original_grayscale_8bit = utils.array_to_img(original_grayscale_8bit_array, scale=False) original_grayscale_8bit.save(filename_grayscale_8bit) original_grayscale_16bit_array = np.array( np.random.randint(-2147483648, 2147483647, (100, 100, 1)), dtype=np.int16 ) original_grayscale_16bit = utils.array_to_img(original_grayscale_16bit_array, scale=False, dtype='int16') original_grayscale_16bit.save(filename_grayscale_16bit) original_grayscale_32bit_array = np.array( np.random.randint(-2147483648, 2147483647, (100, 100, 1)), dtype=np.int32 ) original_grayscale_32bit = utils.array_to_img(original_grayscale_32bit_array, scale=False, dtype='int32') original_grayscale_32bit.save(filename_grayscale_32bit) # Test that loaded image is exactly equal to original. loaded_im = utils.load_img(filename_rgb) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == original_rgb_array.shape assert np.all(loaded_im_array == original_rgb_array) loaded_im = utils.load_img(filename_rgba, color_mode='rgba') loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == original_rgba_array.shape assert np.all(loaded_im_array == original_rgba_array) loaded_im = utils.load_img(filename_rgb, color_mode='grayscale') loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == (original_rgb_array.shape[0], original_rgb_array.shape[1], 1) loaded_im = utils.load_img(filename_grayscale_8bit, color_mode='grayscale') loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == original_grayscale_8bit_array.shape assert np.all(loaded_im_array == original_grayscale_8bit_array) loaded_im = utils.load_img(filename_grayscale_16bit, color_mode='grayscale') loaded_im_array = utils.img_to_array(loaded_im, dtype='int16') assert loaded_im_array.shape == original_grayscale_16bit_array.shape assert np.all(loaded_im_array == original_grayscale_16bit_array) # test casting int16 image to float32 loaded_im_array = utils.img_to_array(loaded_im) assert np.allclose(loaded_im_array, original_grayscale_16bit_array) loaded_im = utils.load_img(filename_grayscale_32bit, color_mode='grayscale') loaded_im_array = utils.img_to_array(loaded_im, dtype='int32') assert loaded_im_array.shape == original_grayscale_32bit_array.shape assert np.all(loaded_im_array == original_grayscale_32bit_array) # test casting int32 image to float32 loaded_im_array = utils.img_to_array(loaded_im) assert np.allclose(loaded_im_array, original_grayscale_32bit_array) # Test that nothing is changed when target size is equal to original. loaded_im = utils.load_img(filename_rgb, target_size=(100, 100)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == original_rgb_array.shape assert np.all(loaded_im_array == original_rgb_array) loaded_im = utils.load_img(filename_rgba, color_mode='rgba', target_size=(100, 100)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == original_rgba_array.shape assert np.all(loaded_im_array == original_rgba_array) loaded_im = utils.load_img(filename_rgb, color_mode='grayscale', target_size=(100, 100)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == (original_rgba_array.shape[0], original_rgba_array.shape[1], 1) loaded_im = utils.load_img(filename_grayscale_8bit, color_mode='grayscale', target_size=(100, 100)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == original_grayscale_8bit_array.shape assert np.all(loaded_im_array == original_grayscale_8bit_array) loaded_im = utils.load_img(filename_grayscale_16bit, color_mode='grayscale', target_size=(100, 100)) loaded_im_array = utils.img_to_array(loaded_im, dtype='int16') assert loaded_im_array.shape == original_grayscale_16bit_array.shape assert np.all(loaded_im_array == original_grayscale_16bit_array) loaded_im = utils.load_img(filename_grayscale_32bit, color_mode='grayscale', target_size=(100, 100)) loaded_im_array = utils.img_to_array(loaded_im, dtype='int32') assert loaded_im_array.shape == original_grayscale_32bit_array.shape assert np.all(loaded_im_array == original_grayscale_32bit_array) # Test down-sampling with bilinear interpolation. loaded_im = utils.load_img(filename_rgb, target_size=(25, 25)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == (25, 25, 3) loaded_im = utils.load_img(filename_rgba, color_mode='rgba', target_size=(25, 25)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == (25, 25, 4) loaded_im = utils.load_img(filename_rgb, color_mode='grayscale', target_size=(25, 25)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == (25, 25, 1) loaded_im = utils.load_img(filename_grayscale_8bit, color_mode='grayscale', target_size=(25, 25)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == (25, 25, 1) loaded_im = utils.load_img(filename_grayscale_16bit, color_mode='grayscale', target_size=(25, 25)) loaded_im_array = utils.img_to_array(loaded_im, dtype='int16') assert loaded_im_array.shape == (25, 25, 1) loaded_im = utils.load_img(filename_grayscale_32bit, color_mode='grayscale', target_size=(25, 25)) loaded_im_array = utils.img_to_array(loaded_im, dtype='int32') assert loaded_im_array.shape == (25, 25, 1) # Test down-sampling with nearest neighbor interpolation. loaded_im_nearest = utils.load_img(filename_rgb, target_size=(25, 25), interpolation="nearest") loaded_im_array_nearest = utils.img_to_array(loaded_im_nearest) assert loaded_im_array_nearest.shape == (25, 25, 3) assert np.any(loaded_im_array_nearest != loaded_im_array) loaded_im_nearest = utils.load_img(filename_rgba, color_mode='rgba', target_size=(25, 25), interpolation="nearest") loaded_im_array_nearest = utils.img_to_array(loaded_im_nearest) assert loaded_im_array_nearest.shape == (25, 25, 4) assert np.any(loaded_im_array_nearest != loaded_im_array) loaded_im = utils.load_img(filename_grayscale_8bit, color_mode='grayscale', target_size=(25, 25), interpolation="nearest") loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == (25, 25, 1) loaded_im = utils.load_img(filename_grayscale_16bit, color_mode='grayscale', target_size=(25, 25), interpolation="nearest") loaded_im_array = utils.img_to_array(loaded_im, dtype='int16') assert loaded_im_array.shape == (25, 25, 1) loaded_im = utils.load_img(filename_grayscale_32bit, color_mode='grayscale', target_size=(25, 25), interpolation="nearest") loaded_im_array = utils.img_to_array(loaded_im, dtype='int32') assert loaded_im_array.shape == (25, 25, 1) # Check that exception is raised if interpolation not supported. loaded_im = utils.load_img(filename_rgb, interpolation="unsupported") with pytest.raises(ValueError): loaded_im = utils.load_img(filename_rgb, target_size=(25, 25), interpolation="unsupported")
def _get_batches_of_transformed_samples(self, index_array): """Gets a batch of transformed samples. # Arguments index_array: Array of sample indices to include in batch. # Returns A batch of transformed samples in one-hot-encoded format. """ additional_bg_class = 0 if self.include_background: additional_bg_class = 1 batch_x = np.zeros( (len(index_array), ) + (self.target_size[0], self.target_size[1], self.num_classes + additional_bg_class), dtype=self.dtype) # build batch of image data # self.filepaths is dynamic, is better to call it once outside the loop filepaths = self.filepaths known_label_keys = self.dropped_labels_memory.keys() known_label_drops = {} unset_label_drops = [] for i, j in enumerate(index_array): if j in known_label_keys: known_label_drops[i] = j else: unset_label_drops.append(i) one_hot_map = np.zeros((self.target_size[0], self.target_size[1], self.num_classes + additional_bg_class), dtype=np.float32) # Iterate over all classes params = None reserved_pixels = None for k in range(self.num_classes): filepath = os.path.join(self.directory, self._mask_classes[k], filepaths[j]) img = load_img(filepath, color_mode=self.color_mode, target_size=self.target_size, interpolation=self.interpolation) x = img_to_array(img, data_format=self.data_format) # Pillow images should be closed after `load_img`, # but not PIL images. if hasattr(img, 'close'): img.close() if self.image_data_generator: # Params need to be set once for every image (not for every mask) if params is None: params = self.image_data_generator.get_random_transform( x.shape) x = self.image_data_generator.apply_transform(x, params) x = self.image_data_generator.standardize(x) if reserved_pixels is None: reserved_pixels = np.zeros(x.shape) x = np.where(reserved_pixels, 0, x) reserved_pixels += x one_hot_map += self.get_one_hot_map( x, k, background=self.background_color, additional_bg_class=additional_bg_class) # If one_hot_map has a max value >1 whe have overlapping classes -> prohibited one_hot_map = one_hot_map.numpy() if one_hot_map.max() > 1: raise ValueError( 'Mask mismatch: classes are not mutually exclusive (multiple class definitions for ' 'one pixel).') if self.include_background: # Background class is everywhere, where the one-hot encoding has only zeros one_hot_map = tf.where( tf.repeat(tf.reshape( tf.math.count_nonzero( one_hot_map == tf.zeros(self.num_classes + 1), axis=2), [img.height, img.width, 1]), self.num_classes + 1, axis=2) == self.num_classes + 1, tf.one_hot( tf.constant(self.num_classes, shape=one_hot_map.shape[:2]), self.num_classes + 1), one_hot_map) batch_x[i] = one_hot_map # optionally save augmented images to disk for debugging purposes if self.save_to_dir: for i, j in enumerate(index_array): img = array_to_img(batch_x[i], self.data_format, scale=True) fname = '{prefix}_{index}_{hash}.{format}'.format( prefix=self.save_prefix, index=j, hash=np.random.randint(1e7), format=self.save_format) img.save(os.path.join(self.save_to_dir, fname)) # Only where labels are not already known if len(self.heterogeneously_labeled_masks) > 0: batch_x[unset_label_drops] = self.remove_masks( np.take(batch_x, unset_label_drops, axis=0)) # Known labels for item in known_label_drops.items(): index_in_batch = item[0] index_in_memory = item[1] memory_binary_mask = self.dropped_labels_memory.get( index_in_memory) batch_x[index_in_batch, :, :, :][ memory_binary_mask] = DELETED_MASK_IDENTIFIER # Extend Memory of known deletion masks. delete_mask = np.where(batch_x == DELETED_MASK_IDENTIFIER, True, False) for i in range(len(index_array)): self.dropped_labels_memory[index_array[i]] = delete_mask[ i, :, :, :] return batch_x
def _get_batches_of_transformed_samples(self, index_array): # IMPORTANT: the next line is changed with respect to the original # keras implementation # Change: self.target_shape <-- list(self.x.shape)[1:] # Additionally: support for more than one augmentation per image batch_x = np.zeros(tuple([len(index_array) * self.n_aug] \ + self.target_shape), dtype=self.dtype) batch_y_id = np.zeros([len(index_array) * self.n_aug] * 2, dtype=np.uint8) for i, j in enumerate(index_array): batch_y_id[i * self.n_aug:i * self.n_aug + self.n_aug, i * self.n_aug:i * self.n_aug + self.n_aug] = 1 for k in range(self.n_aug): x = self.x[j] params = self.image_data_generator.get_random_transform( x.shape) x = self.image_data_generator.apply_transform( x.astype(self.dtype), params) x = self.image_data_generator.standardize(x) batch_x[i * self.n_aug + k] = x if self.n_aug > 1: batch_y_id[np.tril_indices(batch_y_id.shape[0])] = 0 if self.save_to_dir: for i, j in enumerate(index_array): img = array_to_img(batch_x[i], self.data_format, scale=True) fname = '{prefix}_{index}_{hash}.{format}'.format( prefix=self.save_prefix, index=j, hash=np.random.randint(1e4), format=self.save_format) img.save(os.path.join(self.save_to_dir, fname)) # Re-shuffle, in order to avoid contiguous augmented images if (self.n_aug > 1) & (self.shuffle): if self.seed is not None: np.random.seed(self.seed + self.total_batches_seen) idx = np.random.permutation(batch_x.shape[0]) else: idx = np.arange(batch_x.shape[0]) batch_x = batch_x[idx] batch_x_miscs = [xx[index_array][idx] for xx in self.x_misc] output = (batch_x if batch_x_miscs == [] else [batch_x] + batch_x_miscs, ) if self.y is None: return output[0] batch_y_cat = np.repeat(self.y[index_array], self.n_aug, axis=0)[idx] batch_y_id = batch_y_id[idx][:, idx] batch_y = [batch_y_cat, batch_y_id] batch_y_miscs = [yy[indey_array][idx] for yy in self.y_misc] output += (batch_y if batch_y_miscs == [] else batch_y + batch_y_miscs, ) if self.sample_weight is not None: output += (np.repeat(self.sample_weight[index_array], self.n_aug, axis=0)[idx], ) return output
def _get_batches_of_transformed_samples(self, index_array): """Gets a batch of transformed samples. # Arguments index_array: Array of sample indices to include in batch. # Returns A batch of transformed samples. """ index_array = self.X[index_array] batch_x = np.zeros((len(index_array), ) + self.image_shape, dtype=self.dtype) # build batch of image data # self.filepaths is dynamic, is better to call it once outside the loop filepaths = self.filepaths for i, j in enumerate(index_array): img = load_img(filepaths[j], color_mode=self.color_mode, target_size=self.target_size, interpolation=self.interpolation) x = img_to_array(img, data_format=self.data_format) # Pillow images should be closed after `load_img`, # but not PIL images. if hasattr(img, 'close'): img.close() if self.image_data_generator: params = self.image_data_generator.get_random_transform( x.shape) x = self.image_data_generator.apply_transform(x, params) x = self.image_data_generator.standardize(x) batch_x[i] = x # optionally save augmented images to disk for debugging purposes if self.save_to_dir: for i, j in enumerate(index_array): img = array_to_img(batch_x[i], self.data_format, scale=True) fname = '{prefix}_{index}_{hash}.{format}'.format( prefix=self.save_prefix, index=j, hash=np.random.randint(1e7), format=self.save_format) img.save(os.path.join(self.save_to_dir, fname)) # build batch of labels if self.class_mode == 'input': batch_y = batch_x.copy() elif self.class_mode in {'binary', 'sparse'}: batch_y = np.empty(len(batch_x), dtype=self.dtype) for i, n_observation in enumerate(index_array): batch_y[i] = self.classes[n_observation] elif self.class_mode == 'categorical': batch_y = np.zeros((len(batch_x), len(self.class_indices)), dtype=self.dtype) for i, n_observation in enumerate(index_array): batch_y[i, self.classes[n_observation]] = 1. elif self.class_mode == 'multi_output': batch_y = [output[index_array] for output in self.labels] elif self.class_mode == 'raw': batch_y = self.labels[index_array] else: return batch_x if self.sample_weight is None: return batch_x, batch_y else: return batch_x, batch_y, self.sample_weight[index_array]
def sample(self, X=None, sample_size=None, standardize=True): """ Retrived fix-sized image tersors Parameters ---------- X : 2D-array. Default is None Expanded sub-index array of the dataframe. If None, X = np.arange(n_samples)[:, np.newaxis]. sample_size : int. Default is None. The number of samples to be retrieved. If None, sample_size = X.shape[0] standardize : bool. Default is True. Whether to transform the image tersor data. If False, return direct results of `img_to_array`. """ if X is None: X = np.arange(self.dataframe.shape[0])[:, np.newaxis] if not sample_size: sample_size = X.shape[0] retrieved_X = np.zeros((sample_size, ) + self.image_shape, dtype=self.dtype) filepaths = self.filepaths indices = np.squeeze(X) sample_index = self.rng_.choice(indices, size=sample_size, replace=False) for i, j in enumerate(sample_index): img = load_img(filepaths[j], color_mode=self.color_mode, target_size=self.target_size, interpolation=self.interpolation) x = img_to_array(img, data_format=self.data_format) if hasattr(img, 'close'): img.close() if not standardize: retrieved_X[i] = x continue params = self.get_random_transform(x.shape) x = self.apply_transform(x, params) x = self.standardize(x) retrieved_X[i] = x if self.save_to_dir: for i, j in enumerate(sample_index): img = array_to_img(retrieved_X[i], self.data_format, scale=True) fname = '{prefix}_{index}_{hash}.{format}'.format( prefix=self.save_prefix, index=j, hash=np.random.randint(1e7), format=self.save_format) img.save(os.path.join(self.save_to_dir, fname)) # retrieve labels if self.class_mode == 'input': retrieved_y = retrieved_X.copy() elif self.class_mode in {'binary', 'sparse'}: retrieved_y = np.empty(sample_size, dtype=self.dtype) for i, n_observation in enumerate(sample_index): retrieved_y[i] = self.classes[n_observation] elif self.class_mode == 'categorical': retrieved_y = np.zeros((sample_size, len(self.class_indices)), dtype=self.dtype) for i, n_observation in enumerate(sample_index): retrieved_y[i, self.classes[n_observation]] = 1. elif self.class_mode == 'multi_output': retrieved_y = [output[sample_index] for output in self.labels] elif self.class_mode == 'raw': retrieved_y = self.labels[sample_index] else: return retrieved_X return retrieved_X, retrieved_y
def _get_batches_of_transformed_samples(self, index_array): """Gets a batch of transformed samples. # Arguments index_array: Array of sample indices to include in batch. # Returns A batch of transformed samples. """ y = self.classes[index_array] # creo una matrice indice - classe batch = np.concatenate( [np.expand_dims(index_array, 1), np.expand_dims(y, 1)], axis=1) batch = pd.DataFrame(batch, columns=['idx', 'class']) batch = batch.groupby('class') # Per ogni classe genero K sample # batch totale 128 try: batch = batch.apply( lambda _x: _x.sample(18).reset_index(drop=True)) except ValueError: batch = batch.apply( lambda _x: _x.sample(18, replace=True).reset_index(drop=True)) print("This batch is garbage") index_array = np.array(batch['idx']) index_array = np.random.permutation(index_array) batch_x = np.zeros((len(index_array), ) + self.image_shape, dtype=self.dtype) # build batch of image data # self.filepaths is dynamic, is better to call it once outside the loop filepaths = self.filepaths for i, j in enumerate(index_array): img = load_img(filepaths[j], color_mode=self.color_mode, target_size=self.target_size, interpolation=self.interpolation) x = img_to_array(img, data_format=self.data_format) # Pillow images should be closed after `load_img`, # but not PIL images. if hasattr(img, 'close'): img.close() if self.image_data_generator: params = self.image_data_generator.get_random_transform( x.shape) x = self.image_data_generator.apply_transform(x, params) x = self.image_data_generator.standardize(x) batch_x[i] = x # optionally save augmented images to disk for debugging purposes if self.save_to_dir: for i, j in enumerate(index_array): img = array_to_img(batch_x[i], self.data_format, scale=True) fname = '{prefix}_{index}_{hash}.{format}'.format( prefix=self.save_prefix, index=j, hash=np.random.randint(1e7), format=self.save_format) img.save(os.path.join(self.save_to_dir, fname)) # build batch of labels if self.class_mode == 'input': batch_y = batch_x.copy() elif self.class_mode in {'binary', 'sparse'}: batch_y = np.empty(len(batch_x), dtype=self.dtype) for i, n_observation in enumerate(index_array): batch_y[i] = self.classes[n_observation] elif self.class_mode == 'categorical': batch_y = np.zeros((len(batch_x), len(self.class_indices)), dtype=self.dtype) for i, n_observation in enumerate(index_array): batch_y[i, self.classes[n_observation]] = 1. elif self.class_mode == 'multi_output': batch_y = [output[index_array] for output in self.labels] elif self.class_mode == 'raw': batch_y = self.labels[index_array] else: return batch_x if self.sample_weight is None: return [batch_x, batch_x, batch_x, np.argmax(batch_y, axis=1)],\ [np.zeros((len(batch_x), 4096), dtype='float16'), batch_y] else: return batch_x, batch_y, self.sample_weight[index_array]
def write_sample_image(tmpdir): im = utils.array_to_img(np.random.rand(1, 1, 3)) path = str(tmpdir / 'sample_image.png') utils.save_img(path, im) return path
def test_load_img(tmpdir): filename_rgb = str(tmpdir / 'rgb_utils.png') filename_rgba = str(tmpdir / 'rgba_utils.png') filename_grayscale_8bit = str(tmpdir / 'grayscale_8bit_utils.png') filename_grayscale_16bit = str(tmpdir / 'grayscale_16bit_utils.tiff') filename_grayscale_32bit = str(tmpdir / 'grayscale_32bit_utils.tiff') original_rgb_array = np.array(255 * np.random.rand(100, 100, 3), dtype=np.uint8) original_rgb = utils.array_to_img(original_rgb_array, scale=False) original_rgb.save(filename_rgb) original_rgba_array = np.array(255 * np.random.rand(100, 100, 4), dtype=np.uint8) original_rgba = utils.array_to_img(original_rgba_array, scale=False) original_rgba.save(filename_rgba) original_grayscale_8bit_array = np.array(255 * np.random.rand(100, 100, 1), dtype=np.uint8) original_grayscale_8bit = utils.array_to_img(original_grayscale_8bit_array, scale=False) original_grayscale_8bit.save(filename_grayscale_8bit) original_grayscale_16bit_array = np.array(np.random.randint( -2147483648, 2147483647, (100, 100, 1)), dtype=np.int16) original_grayscale_16bit = utils.array_to_img( original_grayscale_16bit_array, scale=False, dtype='int16') original_grayscale_16bit.save(filename_grayscale_16bit) original_grayscale_32bit_array = np.array(np.random.randint( -2147483648, 2147483647, (100, 100, 1)), dtype=np.int32) original_grayscale_32bit = utils.array_to_img( original_grayscale_32bit_array, scale=False, dtype='int32') original_grayscale_32bit.save(filename_grayscale_32bit) # Test that loaded image is exactly equal to original. loaded_im = utils.load_img(filename_rgb) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == original_rgb_array.shape assert np.all(loaded_im_array == original_rgb_array) loaded_im = utils.load_img(filename_rgba, color_mode='rgba') loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == original_rgba_array.shape assert np.all(loaded_im_array == original_rgba_array) loaded_im = utils.load_img(filename_rgb, color_mode='grayscale') loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == (original_rgb_array.shape[0], original_rgb_array.shape[1], 1) loaded_im = utils.load_img(filename_grayscale_8bit, color_mode='grayscale') loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == original_grayscale_8bit_array.shape assert np.all(loaded_im_array == original_grayscale_8bit_array) loaded_im = utils.load_img(filename_grayscale_16bit, color_mode='grayscale') loaded_im_array = utils.img_to_array(loaded_im, dtype='int16') assert loaded_im_array.shape == original_grayscale_16bit_array.shape assert np.all(loaded_im_array == original_grayscale_16bit_array) # test casting int16 image to float32 loaded_im_array = utils.img_to_array(loaded_im) assert np.allclose(loaded_im_array, original_grayscale_16bit_array) loaded_im = utils.load_img(filename_grayscale_32bit, color_mode='grayscale') loaded_im_array = utils.img_to_array(loaded_im, dtype='int32') assert loaded_im_array.shape == original_grayscale_32bit_array.shape assert np.all(loaded_im_array == original_grayscale_32bit_array) # test casting int32 image to float32 loaded_im_array = utils.img_to_array(loaded_im) assert np.allclose(loaded_im_array, original_grayscale_32bit_array) # Test that nothing is changed when target size is equal to original. loaded_im = utils.load_img(filename_rgb, target_size=(100, 100)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == original_rgb_array.shape assert np.all(loaded_im_array == original_rgb_array) loaded_im = utils.load_img(filename_rgba, color_mode='rgba', target_size=(100, 100)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == original_rgba_array.shape assert np.all(loaded_im_array == original_rgba_array) loaded_im = utils.load_img(filename_rgb, color_mode='grayscale', target_size=(100, 100)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == (original_rgba_array.shape[0], original_rgba_array.shape[1], 1) loaded_im = utils.load_img(filename_grayscale_8bit, color_mode='grayscale', target_size=(100, 100)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == original_grayscale_8bit_array.shape assert np.all(loaded_im_array == original_grayscale_8bit_array) loaded_im = utils.load_img(filename_grayscale_16bit, color_mode='grayscale', target_size=(100, 100)) loaded_im_array = utils.img_to_array(loaded_im, dtype='int16') assert loaded_im_array.shape == original_grayscale_16bit_array.shape assert np.all(loaded_im_array == original_grayscale_16bit_array) loaded_im = utils.load_img(filename_grayscale_32bit, color_mode='grayscale', target_size=(100, 100)) loaded_im_array = utils.img_to_array(loaded_im, dtype='int32') assert loaded_im_array.shape == original_grayscale_32bit_array.shape assert np.all(loaded_im_array == original_grayscale_32bit_array) # Test down-sampling with bilinear interpolation. loaded_im = utils.load_img(filename_rgb, target_size=(25, 25)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == (25, 25, 3) loaded_im = utils.load_img(filename_rgba, color_mode='rgba', target_size=(25, 25)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == (25, 25, 4) loaded_im = utils.load_img(filename_rgb, color_mode='grayscale', target_size=(25, 25)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == (25, 25, 1) loaded_im = utils.load_img(filename_grayscale_8bit, color_mode='grayscale', target_size=(25, 25)) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == (25, 25, 1) loaded_im = utils.load_img(filename_grayscale_16bit, color_mode='grayscale', target_size=(25, 25)) loaded_im_array = utils.img_to_array(loaded_im, dtype='int16') assert loaded_im_array.shape == (25, 25, 1) loaded_im = utils.load_img(filename_grayscale_32bit, color_mode='grayscale', target_size=(25, 25)) loaded_im_array = utils.img_to_array(loaded_im, dtype='int32') assert loaded_im_array.shape == (25, 25, 1) # Test down-sampling with nearest neighbor interpolation. loaded_im_nearest = utils.load_img(filename_rgb, target_size=(25, 25), interpolation="nearest") loaded_im_array_nearest = utils.img_to_array(loaded_im_nearest) assert loaded_im_array_nearest.shape == (25, 25, 3) assert np.any(loaded_im_array_nearest != loaded_im_array) loaded_im_nearest = utils.load_img(filename_rgba, color_mode='rgba', target_size=(25, 25), interpolation="nearest") loaded_im_array_nearest = utils.img_to_array(loaded_im_nearest) assert loaded_im_array_nearest.shape == (25, 25, 4) assert np.any(loaded_im_array_nearest != loaded_im_array) loaded_im = utils.load_img(filename_grayscale_8bit, color_mode='grayscale', target_size=(25, 25), interpolation="nearest") loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == (25, 25, 1) loaded_im = utils.load_img(filename_grayscale_16bit, color_mode='grayscale', target_size=(25, 25), interpolation="nearest") loaded_im_array = utils.img_to_array(loaded_im, dtype='int16') assert loaded_im_array.shape == (25, 25, 1) loaded_im = utils.load_img(filename_grayscale_32bit, color_mode='grayscale', target_size=(25, 25), interpolation="nearest") loaded_im_array = utils.img_to_array(loaded_im, dtype='int32') assert loaded_im_array.shape == (25, 25, 1) # Check that exception is raised if interpolation not supported. loaded_im = utils.load_img(filename_rgb, interpolation="unsupported") with pytest.raises(ValueError): loaded_im = utils.load_img(filename_rgb, target_size=(25, 25), interpolation="unsupported") # Check that the aspect ratio of a square is the same filename_red_square = str(tmpdir / 'red_square_utils.png') A = np.zeros((50, 100, 3), dtype=np.uint8) # rectangle image 100x50 A[20:30, 45:55, 0] = 255 # red square 10x10 red_square_array = np.array(A) red_square = utils.array_to_img(red_square_array, scale=False) red_square.save(filename_red_square) loaded_im = utils.load_img(filename_red_square, target_size=(25, 25), keep_aspect_ratio=True) loaded_im_array = utils.img_to_array(loaded_im) assert loaded_im_array.shape == (25, 25, 3) red_channel_arr = loaded_im_array[:, :, 0].astype(np.bool) square_width = np.sum(np.sum(red_channel_arr, axis=0)) square_height = np.sum(np.sum(red_channel_arr, axis=1)) aspect_ratio_result = square_width / square_height # original square had 1:1 ratio assert aspect_ratio_result == pytest.approx(1.0)