def _parse_and_store_boxes(filename, dataset_directory, orig_dims): filename_split = tf.unstack(tf.string_split([filename], "_").values[:-1], num=3) strip_filename = tf.string_join(filename_split, "_") txt_dir = tf.cast(os.path.join(dataset_directory, 'panoptic_txt_weights/'), tf.string) txt_ext = tf.cast('_gtFine_instanceIds.txt', tf.string) txt_filename = tf.string_join([txt_dir, strip_filename, txt_ext]) la_in_txt = tf.read_file(txt_filename) la_in_txt = tf.string_split([la_in_txt], delimiter='\n').values la_in_txt = tf.string_split(la_in_txt, delimiter=' ').values la_in_int = tf.reshape(tf.string_to_number(la_in_txt, out_type=tf.int32), [-1, 7]) # i_ids = la_in_int[:, 0] weights = la_in_int[:, 6] boxes_orig = la_in_int[:, 2:6] boxes_format = convert_input_box_format(boxes_orig) boxes_norm = normalize_boxes(boxes_format, orig_height=orig_dims[0], orig_width=orig_dims[1]) classes = la_in_int[:, 1] instance_ids = la_in_int[:, 0] return boxes_norm, classes, weights, instance_ids
def _serving_model_graph(features, params): """Build the model graph for serving.""" images = features['images'] _, height, width, _ = images.get_shape().as_list() input_anchor = anchor.Anchor(params.anchor.min_level, params.anchor.max_level, params.anchor.num_scales, params.anchor.aspect_ratios, params.anchor.anchor_size, (height, width)) model_fn = factory.model_generator(params) model_outputs = model_fn.build_outputs( features['images'], labels={'anchor_boxes': input_anchor.multilevel_boxes}, mode=mode_keys.PREDICT) if cast_num_detections_to_float: model_outputs['num_detections'] = tf.cast( model_outputs['num_detections'], dtype=tf.float32) if output_image_info: model_outputs.update({ 'image_info': features['image_info'], }) if output_normalized_coordinates: model_outputs['detection_boxes'] = box_utils.normalize_boxes( model_outputs['detection_boxes'], features['image_info'][:, 1:2, :]) return model_outputs
def _serving_model_graph(features, params): """Build the model graph for serving.""" images = features['images'] batch_size, height, width, _ = images.get_shape().as_list() input_anchor = anchor.Anchor( params.anchor.min_level, params.anchor.max_level, params.anchor.num_scales, params.anchor.aspect_ratios, params.anchor.anchor_size, (height, width)) multilevel_boxes = {} for k, v in six.iteritems(input_anchor.multilevel_boxes): multilevel_boxes[k] = tf.tile( tf.expand_dims(v, 0), [batch_size, 1, 1]) model_fn = factory.model_generator(params) model_outputs = model_fn.build_outputs( features['images'], labels={ 'anchor_boxes': multilevel_boxes, 'image_info': features['image_info'], }, mode=mode_keys.PREDICT) if cast_num_detections_to_float: model_outputs['num_detections'] = tf.cast( model_outputs['num_detections'], dtype=tf.float32) if output_image_info: model_outputs.update({ 'image_info': features['image_info'], }) if output_normalized_coordinates: model_outputs['detection_boxes'] = box_utils.normalize_boxes( model_outputs['detection_boxes'], features['image_info'][:, 1:2, :]) predictions = { 'num_detections': tf.identity( model_outputs['num_detections'], 'NumDetections'), 'detection_boxes': tf.identity( model_outputs['detection_boxes'], 'DetectionBoxes'), 'detection_classes': tf.identity( model_outputs['detection_classes'], 'DetectionClasses'), 'detection_scores': tf.identity( model_outputs['detection_scores'], 'DetectionScores'), } if 'detection_masks' in model_outputs: predictions.update({ 'detection_masks': tf.identity(model_outputs['detection_masks'], 'DetectionMasks'), }) if output_image_info: predictions['image_info'] = tf.identity( model_outputs['image_info'], 'ImageInfo') return predictions
def _predict_rpn(self, features): with tf.variable_scope("RPN"): anchors = anchor_generator.generate( base_size=self._anchor_size, stride=self._anchor_stride, scales=self._anchor_scales, ratios=self._anchor_ratios, features_height=tf.shape(features)[1], features_width=tf.shape(features)[2], offset=self._anchor_offset) anchors_normalized = box_utils.normalize_boxes( anchors, self.params.height_input, self.params.width_input) rpn_sliding_window = slim.conv2d(features, 512, kernel_size=[3, 3], activation_fn=tf.nn.relu, scope='sliding_window') rpn_objectness = slim.conv2d(rpn_sliding_window, self.num_anchors_per_location * 2, kernel_size=[1, 1], activation_fn=None, padding="VALID", scope='objectness') rpn_box_encoded = slim.conv2d(rpn_sliding_window, self.num_anchors_per_location * 4, kernel_size=[1, 1], activation_fn=None, padding="VALID", scope='box') rpn_objectness = tf.reshape(rpn_objectness, [self.params.Nb, -1, 2]) rpn_box_encoded = tf.reshape(rpn_box_encoded, [self.params.Nb, -1, 4]) prediction_dict = { 'rpn_objectness': rpn_objectness, 'rpn_box_encoded': rpn_box_encoded, 'anchors': anchors, 'anchors_normalized': anchors_normalized } print(prediction_dict) return prediction_dict
def visualize_images_with_bounding_boxes(images, box_outputs, step, summary_writer): """Records subset of evaluation images with bounding boxes.""" if not isinstance(images, list): logging.warning('visualize_images_with_bounding_boxes expects list of ' 'images but received type: %s and value: %s', type(images), images) return image_shape = tf.shape(images[0]) image_height = tf.cast(image_shape[0], tf.float32) image_width = tf.cast(image_shape[1], tf.float32) normalized_boxes = box_utils.normalize_boxes(box_outputs, [image_height, image_width]) bounding_box_color = tf.constant([[1.0, 1.0, 0.0, 1.0]]) image_summary = tf.image.draw_bounding_boxes( tf.cast(images, tf.float32), normalized_boxes, bounding_box_color) with summary_writer.as_default(): tf.summary.image('bounding_box_summary', image_summary, step=step) summary_writer.flush()
def build_predictions(features, params, output_image_info, output_normalized_coordinates, cast_num_detections_to_float, cast_detection_classes_to_float=False): """Builds the model graph for serving. Args: features: features to be passed to the serving model graph params: hyperparameters to be passed to the serving model graph output_image_info: bool, whether output the image_info node. output_normalized_coordinates: bool, whether box outputs are in the normalized coordinates. cast_num_detections_to_float: bool, whether to cast the number of detections to float type. cast_detection_classes_to_float: bool, whether or not cast the detection classes to float type. Returns: predictions: model outputs for serving. model_outputs: a dict of model output tensors. """ images = features['images'] batch_size, height, width, _ = images.get_shape().as_list() input_anchor = anchor.Anchor(params.architecture.min_level, params.architecture.max_level, params.anchor.num_scales, params.anchor.aspect_ratios, params.anchor.anchor_size, (height, width)) multilevel_boxes = {} for k, v in six.iteritems(input_anchor.multilevel_boxes): multilevel_boxes[k] = tf.tile(tf.expand_dims(v, 0), [batch_size, 1, 1]) model_fn = factory.model_generator(params) model_outputs = model_fn.build_outputs(features['images'], labels={ 'anchor_boxes': multilevel_boxes, 'image_info': features['image_info'], }, mode=mode_keys.PREDICT) # Return flattened raw outputs. if not params.postprocess.apply_nms: predictions = { 'raw_boxes': tf.identity(model_outputs['raw_boxes'], 'RawBoxes'), 'raw_scores': tf.identity(model_outputs['raw_scores'], 'RawScores'), } return predictions, model_outputs if cast_num_detections_to_float: model_outputs['num_detections'] = tf.cast( model_outputs['num_detections'], dtype=tf.float32) if cast_detection_classes_to_float: model_outputs['detection_classes'] = tf.cast( model_outputs['detection_classes'], dtype=tf.float32) if output_image_info: model_outputs.update({ 'image_info': features['image_info'], }) if output_normalized_coordinates: detection_boxes = ( model_outputs['detection_boxes'] / tf.tile(features['image_info'][:, 2:3, :], [1, 1, 2])) model_outputs['detection_boxes'] = box_utils.normalize_boxes( detection_boxes, features['image_info'][:, 0:1, :]) predictions = { 'num_detections': tf.identity(model_outputs['num_detections'], 'NumDetections'), 'detection_boxes': tf.identity(model_outputs['detection_boxes'], 'DetectionBoxes'), 'detection_classes': tf.identity(model_outputs['detection_classes'], 'DetectionClasses'), 'detection_scores': tf.identity(model_outputs['detection_scores'], 'DetectionScores'), } if 'detection_masks' in model_outputs: predictions.update({ 'detection_masks': tf.identity(model_outputs['detection_masks'], 'DetectionMasks'), }) if 'detection_outer_boxes' in model_outputs: predictions.update({ 'detection_outer_boxes': tf.identity(model_outputs['detection_outer_boxes'], 'DetectionOuterBoxes'), }) if output_image_info: predictions['image_info'] = tf.identity(model_outputs['image_info'], 'ImageInfo') return predictions, model_outputs
def _parse_train_data(self, data): """Parses data for training. Args: data: the decoded tensor dictionary from TfExampleDecoder. Returns: image: image tensor that is preproessed to have normalized value and dimension [output_size[0], output_size[1], 3] labels: a dictionary of tensors used for training. The following describes {key: value} pairs in the dictionary. image_info: a 2D `Tensor` that encodes the information of the image and the applied preprocessing. It is in the format of [[original_height, original_width], [scaled_height, scaled_width], anchor_boxes: ordered dictionary with keys [min_level, min_level+1, ..., max_level]. The values are tensor with shape [height_l, width_l, 4] representing anchor boxes at each level. rpn_score_targets: ordered dictionary with keys [min_level, min_level+1, ..., max_level]. The values are tensor with shape [height_l, width_l, anchors_per_location]. The height_l and width_l represent the dimension of class logits at l-th level. rpn_box_targets: ordered dictionary with keys [min_level, min_level+1, ..., max_level]. The values are tensor with shape [height_l, width_l, anchors_per_location * 4]. The height_l and width_l represent the dimension of bounding box regression output at l-th level. gt_boxes: Groundtruth bounding box annotations. The box is represented in [y1, x1, y2, x2] format. The coordinates are w.r.t the scaled image that is fed to the network. The tennsor is padded with -1 to the fixed dimension [self._max_num_instances, 4]. gt_classes: Groundtruth classes annotations. The tennsor is padded with -1 to the fixed dimension [self._max_num_instances]. gt_masks: groundtrugh masks cropped by the bounding box and resized to a fixed size determined by mask_crop_size. """ classes = data['groundtruth_classes'] boxes = data['groundtruth_boxes'] if self._include_mask: masks = data['groundtruth_instance_masks'] is_crowds = data['groundtruth_is_crowd'] # Skips annotations with `is_crowd` = True. if self._skip_crowd_during_training and self._is_training: num_groundtrtuhs = tf.shape(classes)[0] with tf.control_dependencies([num_groundtrtuhs, is_crowds]): indices = tf.cond( tf.greater(tf.size(is_crowds), 0), lambda: tf.where(tf.logical_not(is_crowds))[:, 0], lambda: tf.cast(tf.range(num_groundtrtuhs), tf.int64)) classes = tf.gather(classes, indices) boxes = tf.gather(boxes, indices) if self._include_mask: masks = tf.gather(masks, indices) # Gets original image and its size. image = data['image'] image_shape = tf.shape(image)[0:2] # Normalizes image with mean and std pixel values. image = input_utils.normalize_image(image) # Flips image randomly during training. if self._aug_rand_hflip: if self._include_mask: image, boxes, masks = input_utils.random_horizontal_flip( image, boxes, masks) else: image, boxes = input_utils.random_horizontal_flip(image, boxes) # Converts boxes from normalized coordinates to pixel coordinates. # Now the coordinates of boxes are w.r.t. the original image. boxes = box_utils.denormalize_boxes(boxes, image_shape) # Resizes and crops image. image, image_info = input_utils.resize_and_crop_image( image, self._output_size, padded_size=input_utils.compute_padded_size( self._output_size, 2**self._max_level), aug_scale_min=self._aug_scale_min, aug_scale_max=self._aug_scale_max) image_height, image_width, _ = image.get_shape().as_list() # Resizes and crops boxes. # Now the coordinates of boxes are w.r.t the scaled image. image_scale = image_info[2, :] offset = image_info[3, :] boxes = input_utils.resize_and_crop_boxes(boxes, image_scale, image_info[1, :], offset) # Filters out ground truth boxes that are all zeros. indices = box_utils.get_non_empty_box_indices(boxes) boxes = tf.gather(boxes, indices) classes = tf.gather(classes, indices) if self._include_mask: masks = tf.gather(masks, indices) # Transfer boxes to the original image space and do normalization. cropped_boxes = boxes + tf.tile(tf.expand_dims(offset, axis=0), [1, 2]) cropped_boxes /= tf.tile(tf.expand_dims(image_scale, axis=0), [1, 2]) cropped_boxes = box_utils.normalize_boxes(cropped_boxes, image_shape) num_masks = tf.shape(masks)[0] masks = tf.image.crop_and_resize( tf.expand_dims(masks, axis=-1), cropped_boxes, box_indices=tf.range(num_masks, dtype=tf.int32), crop_size=[self._mask_crop_size, self._mask_crop_size], method='bilinear') masks = tf.squeeze(masks, axis=-1) # Assigns anchor targets. # Note that after the target assignment, box targets are absolute pixel # offsets w.r.t. the scaled image. input_anchor = anchor.Anchor(self._min_level, self._max_level, self._num_scales, self._aspect_ratios, self._anchor_size, (image_height, image_width)) anchor_labeler = anchor.RpnAnchorLabeler(input_anchor, self._rpn_match_threshold, self._rpn_unmatched_threshold, self._rpn_batch_size_per_im, self._rpn_fg_fraction) rpn_score_targets, rpn_box_targets = anchor_labeler.label_anchors( boxes, tf.cast(tf.expand_dims(classes, axis=-1), dtype=tf.float32)) # If bfloat16 is used, casts input image to tf.bfloat16. if self._use_bfloat16: image = tf.cast(image, dtype=tf.bfloat16) # Packs labels for model_fn outputs. labels = { 'anchor_boxes': input_anchor.multilevel_boxes, 'image_info': image_info, 'rpn_score_targets': rpn_score_targets, 'rpn_box_targets': rpn_box_targets, } labels['gt_boxes'] = input_utils.clip_or_pad_to_fixed_size( boxes, self._max_num_instances, -1) labels['gt_classes'] = input_utils.clip_or_pad_to_fixed_size( classes, self._max_num_instances, -1) if self._include_mask: labels['gt_masks'] = input_utils.clip_or_pad_to_fixed_size( masks, self._max_num_instances, -1) return image, labels
def parse_train_data(self, data): """Parse data for ShapeMask training.""" classes = data['groundtruth_classes'] boxes = data['groundtruth_boxes'] masks = data['groundtruth_instance_masks'] is_crowds = data['groundtruth_is_crowd'] # Skips annotations with `is_crowd` = True. if self._skip_crowd_during_training and self._is_training: num_groundtrtuhs = tf.shape(classes)[0] with tf.control_dependencies([num_groundtrtuhs, is_crowds]): indices = tf.cond( tf.greater(tf.size(is_crowds), 0), lambda: tf.where(tf.logical_not(is_crowds))[:, 0], lambda: tf.cast(tf.range(num_groundtrtuhs), tf.int64)) classes = tf.gather(classes, indices) boxes = tf.gather(boxes, indices) masks = tf.gather(masks, indices) # If not using category, makes all categories with id = 0. if not self._use_category: classes = tf.cast(tf.greater(classes, 0), dtype=tf.float32) image = self.get_normalized_image(data) # Flips image randomly during training. if self._aug_rand_hflip: image, boxes, masks = input_utils.random_horizontal_flip( image, boxes, masks) # Converts boxes from normalized coordinates to pixel coordinates. image_shape = tf.shape(image)[0:2] boxes = box_utils.denormalize_boxes(boxes, image_shape) # Resizes and crops image. image, image_info = input_utils.resize_and_crop_image( image, self._output_size, self._output_size, aug_scale_min=self._aug_scale_min, aug_scale_max=self._aug_scale_max) self._train_image_scale = image_info[2, :] self._train_offset = image_info[3, :] # Resizes and crops boxes and masks. boxes = input_utils.resize_and_crop_boxes(boxes, self._train_image_scale, image_info[1, :], self._train_offset) # Filters out ground truth boxes that are all zeros. indices = box_utils.get_non_empty_box_indices(boxes) boxes = tf.gather(boxes, indices) classes = tf.gather(classes, indices) masks = tf.gather(masks, indices) # Assigns anchors. input_anchor = anchor.Anchor(self._min_level, self._max_level, self._num_scales, self._aspect_ratios, self._anchor_size, self._output_size) anchor_labeler = anchor.AnchorLabeler(input_anchor, self._match_threshold, self._unmatched_threshold) (cls_targets, box_targets, num_positives) = anchor_labeler.label_anchors( boxes, tf.cast(tf.expand_dims(classes, axis=1), tf.float32)) # Sample groundtruth masks/boxes/classes for mask branch. num_masks = tf.shape(masks)[0] mask_shape = tf.shape(masks)[1:3] # Pad sampled boxes/masks/classes to a constant batch size. padded_boxes = input_utils.pad_to_fixed_size(boxes, self._num_sampled_masks) padded_classes = input_utils.pad_to_fixed_size(classes, self._num_sampled_masks) padded_masks = input_utils.pad_to_fixed_size(masks, self._num_sampled_masks) # Randomly sample groundtruth masks for mask branch training. For the image # without groundtruth masks, it will sample the dummy padded tensors. rand_indices = tf.random.shuffle( tf.range(tf.maximum(num_masks, self._num_sampled_masks))) rand_indices = tf.mod(rand_indices, tf.maximum(num_masks, 1)) rand_indices = rand_indices[0:self._num_sampled_masks] rand_indices = tf.reshape(rand_indices, [self._num_sampled_masks]) sampled_boxes = tf.gather(padded_boxes, rand_indices) sampled_classes = tf.gather(padded_classes, rand_indices) sampled_masks = tf.gather(padded_masks, rand_indices) # Jitter the sampled boxes to mimic the noisy detections. sampled_boxes = box_utils.jitter_boxes( sampled_boxes, noise_scale=self._box_jitter_scale) sampled_boxes = box_utils.clip_boxes(sampled_boxes, self._output_size) # Compute mask targets in feature crop. A feature crop fully contains a # sampled box. mask_outer_boxes = box_utils.compute_outer_boxes( sampled_boxes, tf.shape(image)[0:2], scale=self._outer_box_scale) mask_outer_boxes = box_utils.clip_boxes(mask_outer_boxes, self._output_size) # Compensate the offset of mask_outer_boxes to map it back to original image # scale. mask_outer_boxes_ori = mask_outer_boxes mask_outer_boxes_ori += tf.tile( tf.expand_dims(self._train_offset, axis=0), [1, 2]) mask_outer_boxes_ori /= tf.tile( tf.expand_dims(self._train_image_scale, axis=0), [1, 2]) norm_mask_outer_boxes_ori = box_utils.normalize_boxes( mask_outer_boxes_ori, mask_shape) # Set sampled_masks shape to [batch_size, height, width, 1]. sampled_masks = tf.cast(tf.expand_dims(sampled_masks, axis=-1), tf.float32) mask_targets = tf.image.crop_and_resize( sampled_masks, norm_mask_outer_boxes_ori, box_ind=tf.range(self._num_sampled_masks), crop_size=[self._mask_crop_size, self._mask_crop_size], method='bilinear', extrapolation_value=0, name='train_mask_targets') mask_targets = tf.where(tf.greater_equal(mask_targets, 0.5), tf.ones_like(mask_targets), tf.zeros_like(mask_targets)) mask_targets = tf.squeeze(mask_targets, axis=-1) if self._up_sample_factor > 1: fine_mask_targets = tf.image.crop_and_resize( sampled_masks, norm_mask_outer_boxes_ori, box_ind=tf.range(self._num_sampled_masks), crop_size=[ self._mask_crop_size * self._up_sample_factor, self._mask_crop_size * self._up_sample_factor ], method='bilinear', extrapolation_value=0, name='train_mask_targets') fine_mask_targets = tf.where( tf.greater_equal(fine_mask_targets, 0.5), tf.ones_like(fine_mask_targets), tf.zeros_like(fine_mask_targets)) fine_mask_targets = tf.squeeze(fine_mask_targets, axis=-1) else: fine_mask_targets = mask_targets # If bfloat16 is used, casts input image to tf.bfloat16. if self._use_bfloat16: image = tf.cast(image, dtype=tf.bfloat16) valid_image = tf.cast(tf.not_equal(num_masks, 0), tf.int32) if self._mask_train_class == 'all': mask_is_valid = valid_image * tf.ones_like(sampled_classes, tf.int32) else: # Get the intersection of sampled classes with training splits. mask_valid_classes = tf.cast( tf.expand_dims( class_utils.coco_split_class_ids(self._mask_train_class), 1), sampled_classes.dtype) match = tf.reduce_any( tf.equal(tf.expand_dims(sampled_classes, 0), mask_valid_classes), 0) mask_is_valid = valid_image * tf.cast(match, tf.int32) # Packs labels for model_fn outputs. labels = { 'cls_targets': cls_targets, 'box_targets': box_targets, 'anchor_boxes': input_anchor.multilevel_boxes, 'num_positives': num_positives, 'image_info': image_info, # For ShapeMask. 'mask_boxes': sampled_boxes, 'mask_outer_boxes': mask_outer_boxes, 'mask_targets': mask_targets, 'fine_mask_targets': fine_mask_targets, 'mask_classes': sampled_classes, 'mask_is_valid': mask_is_valid, } return image, labels
def _parse_train_data(self, data): """Parses data for training. Args: data: the decoded tensor dictionary from TfExampleDecoder. Returns: image: image tensor that is preproessed to have normalized value and dimension [output_size[0], output_size[1], 3] labels: a dictionary of tensors used for training. The following describes {key: value} pairs in the dictionary. image: image tensor that is preproessed to have normalized value and dimension [output_size[0], output_size[1], 3] image_info: a 2D `Tensor` that encodes the information of the image and the applied preprocessing. It is in the format of [[original_height, original_width], [scaled_height, scaled_width], num_groundtrtuhs: number of objects. boxes: Groundtruth bounding box annotations. The box is represented in [y1, x1, y2, x2] format. The coordinates are w.r.t the scaled image that is fed to the network. The tennsor is padded with -1 to the fixed dimension [self._max_num_instances, 4]. classes: Groundtruth classes annotations. The tennsor is padded with -1 to the fixed dimension [self._max_num_instances]. masks: groundtrugh masks cropped by the bounding box and resized to a fixed size determined by mask_crop_size. pasted_objects_mask: a binary tensor with the same size as image which is computed as the union of all the objects masks. """ classes = data['groundtruth_classes'] boxes = data['groundtruth_boxes'] if self._include_mask: masks = data['groundtruth_instance_masks'] is_crowds = data['groundtruth_is_crowd'] # Skips annotations with `is_crowd` = True. if self._skip_crowd_during_training: num_groundtrtuhs = tf.shape(classes)[0] with tf.control_dependencies([num_groundtrtuhs, is_crowds]): indices = tf.cond( tf.greater(tf.size(is_crowds), 0), lambda: tf.where(tf.logical_not(is_crowds))[:, 0], lambda: tf.cast(tf.range(num_groundtrtuhs), tf.int64)) classes = tf.gather(classes, indices) boxes = tf.gather(boxes, indices) if self._include_mask: masks = tf.gather(masks, indices) # Gets original image and its size. image = data['image'] image_shape = tf.shape(image)[0:2] # Normalizes image with mean and std pixel values. image = input_utils.normalize_image(image) # Flips image randomly during training. if self._aug_rand_hflip: if self._include_mask: image, boxes, masks = input_utils.random_horizontal_flip( image, boxes, masks) else: image, boxes = input_utils.random_horizontal_flip(image, boxes) # Converts boxes from normalized coordinates to pixel coordinates. # Now the coordinates of boxes are w.r.t. the original image. boxes = box_utils.denormalize_boxes(boxes, image_shape) # Resizes and crops image. image, image_info = input_utils.resize_and_crop_image( image, self._output_size, padded_size=input_utils.compute_padded_size( self._output_size, 2**self._max_level), aug_scale_min=self._aug_scale_min, aug_scale_max=self._aug_scale_max) # Resizes and crops boxes. # Now the coordinates of boxes are w.r.t the scaled image. image_scale = image_info[2, :] offset = image_info[3, :] boxes = input_utils.resize_and_crop_boxes(boxes, image_scale, image_info[1, :], offset) # Filters out ground truth boxes that are all zeros. indices = box_utils.get_non_empty_box_indices(boxes) boxes = tf.gather(boxes, indices) classes = tf.gather(classes, indices) if self._include_mask: masks = tf.gather(masks, indices) uncropped_masks = tf.cast(masks, tf.int8) uncropped_masks = tf.expand_dims(uncropped_masks, axis=3) uncropped_masks = input_utils.resize_and_crop_masks( uncropped_masks, image_scale, self._output_size, offset) # Transfer boxes to the original image space and do normalization. cropped_boxes = boxes + tf.tile(tf.expand_dims(offset, axis=0), [1, 2]) cropped_boxes /= tf.tile(tf.expand_dims(image_scale, axis=0), [1, 2]) cropped_boxes = box_utils.normalize_boxes(cropped_boxes, image_shape) num_masks = tf.shape(masks)[0] masks = tf.image.crop_and_resize( tf.expand_dims(masks, axis=-1), cropped_boxes, box_indices=tf.range(num_masks, dtype=tf.int32), crop_size=[self._mask_crop_size, self._mask_crop_size], method='bilinear') masks = tf.squeeze(masks, axis=-1) indices = tf.range(start=0, limit=tf.shape(classes)[0], dtype=tf.int32) # Samples the numbers of masks for pasting. m = tf.random.uniform(shape=[], maxval=tf.shape(classes)[0] + 1, dtype=tf.int32) m = tf.math.minimum(m, tf.shape(classes)[0]) # Shuffles the indices of objects and keep the first m objects for pasting. shuffled_indices = tf.random.shuffle(indices) shuffled_indices = tf.slice(shuffled_indices, [0], [m]) boxes = tf.gather(boxes, shuffled_indices) masks = tf.gather(masks, shuffled_indices) classes = tf.gather(classes, shuffled_indices) uncropped_masks = tf.gather(uncropped_masks, shuffled_indices) pasted_objects_mask = tf.reduce_max(uncropped_masks, 0) pasted_objects_mask = tf.cast(pasted_objects_mask, tf.bool) labels = { 'image': image, 'image_info': image_info, 'num_groundtrtuhs': tf.shape(classes)[0], 'boxes': boxes, 'masks': masks, 'classes': classes, 'pasted_objects_mask': pasted_objects_mask, } return labels
def _normalize_box_coordinates(boxes, image_info): boxes = boxes / tf.tile(image_info[:, 2:3, :], [1, 1, 2]) return box_utils.normalize_boxes(boxes, image_info[:, 0:1, :])
def _parse_train_data(self, data): """Parse data for ShapeMask training.""" classes = data['groundtruth_classes'] boxes = data['groundtruth_boxes'] masks = data['groundtruth_instance_masks'] is_crowds = data['groundtruth_is_crowd'] # Skips annotations with `is_crowd` = True. if self._skip_crowd_during_training and self._is_training: num_groundtrtuhs = tf.shape(classes)[0] with tf.control_dependencies([num_groundtrtuhs, is_crowds]): indices = tf.cond( tf.greater(tf.size(is_crowds), 0), lambda: tf.where(tf.logical_not(is_crowds))[:, 0], lambda: tf.cast(tf.range(num_groundtrtuhs), tf.int64)) classes = tf.gather(classes, indices) boxes = tf.gather(boxes, indices) masks = tf.gather(masks, indices) # Gets original image and its size. image = data['image'] image_shape = tf.shape(image)[0:2] # If not using category, makes all categories with id = 0. if not self._use_category: classes = tf.cast(tf.greater(classes, 0), dtype=tf.float32) # Normalizes image with mean and std pixel values. image = input_utils.normalize_image(image) # Flips image randomly during training. if self._aug_rand_hflip: image, boxes, masks = input_utils.random_horizontal_flip( image, boxes, masks) # Converts boxes from normalized coordinates to pixel coordinates. boxes = box_utils.denormalize_boxes(boxes, image_shape) # Resizes and crops image. image, image_info = input_utils.resize_and_crop_image( image, self._output_size, self._output_size, aug_scale_min=self._aug_scale_min, aug_scale_max=self._aug_scale_max) image_scale = image_info[2, :] offset = image_info[3, :] # Resizes and crops boxes and masks. boxes = input_utils.resize_and_crop_boxes(boxes, image_scale, self._output_size, offset) masks = input_utils.resize_and_crop_masks( tf.expand_dims(masks, axis=-1), image_scale, self._output_size, offset) masks = tf.squeeze(masks, axis=-1) # Filters out ground truth boxes that are all zeros. indices = input_utils.get_non_empty_box_indices(boxes) boxes = tf.gather(boxes, indices) classes = tf.gather(classes, indices) masks = tf.gather(masks, indices) # Assigns anchors. input_anchor = anchor.Anchor(self._min_level, self._max_level, self._num_scales, self._aspect_ratios, self._anchor_size, self._output_size) anchor_labeler = anchor.AnchorLabeler(input_anchor, self._match_threshold, self._unmatched_threshold) (cls_targets, box_targets, num_positives) = anchor_labeler.label_anchors( boxes, tf.cast(tf.expand_dims(classes, axis=1), tf.float32)) # Sample groundtruth masks/boxes/classes for mask branch. num_masks = tf.shape(masks)[0] mask_shape = tf.shape(masks)[1:3] # Pad sampled boxes/masks/classes to a constant batch size. padded_boxes = input_utils.pad_to_fixed_size(boxes, self._num_sampled_masks) padded_classes = input_utils.pad_to_fixed_size(classes, self._num_sampled_masks) padded_masks = input_utils.pad_to_fixed_size(masks, self._num_sampled_masks) # Randomly sample groundtruth masks for mask branch training. For the image # without groundtruth masks, it will sample the dummy padded tensors. rand_indices = tf.random.uniform([self._num_sampled_masks], minval=0, maxval=tf.maximum(num_masks, 1), dtype=tf.dtypes.int32) sampled_boxes = tf.gather(padded_boxes, rand_indices) sampled_classes = tf.gather(padded_classes, rand_indices) sampled_masks = tf.gather(padded_masks, rand_indices) # Compute mask targets in feature crop. A feature crop fully contains a # sampled box. mask_outer_boxes = box_utils.compute_outer_boxes( sampled_boxes, mask_shape, scale=self._outer_box_scale) norm_mask_outer_boxes = box_utils.normalize_boxes( mask_outer_boxes, mask_shape) # Set sampled_masks shape to [batch_size, height, width, 1]. sampled_masks = tf.expand_dims(sampled_masks, axis=-1) mask_targets = tf.image.crop_and_resize( sampled_masks, norm_mask_outer_boxes, box_ind=tf.range(self._num_sampled_masks), crop_size=[self._mask_crop_size, self._mask_crop_size], method='bilinear', extrapolation_value=0, name='train_mask_targets') mask_targets = tf.where(tf.greater_equal(mask_targets, 0.5), tf.ones_like(mask_targets), tf.zeros_like(mask_targets)) mask_targets = tf.squeeze(mask_targets, axis=-1) # If bfloat16 is used, casts input image to tf.bfloat16. if self._use_bfloat16: image = tf.cast(image, dtype=tf.bfloat16) # Packs labels for model_fn outputs. labels = { 'cls_targets': cls_targets, 'box_targets': box_targets, 'anchor_boxes': input_anchor.multilevel_boxes, 'num_positives': num_positives, 'image_info': image_info, # For ShapeMask. 'mask_boxes': sampled_boxes, 'mask_outer_boxes': mask_outer_boxes, 'mask_targets': mask_targets, 'mask_classes': sampled_classes, 'mask_is_valid': tf.cast(tf.not_equal(num_masks, 0), tf.int32) } return image, labels
def _parse_train_data_v2(self, data): """Parses data for training. Args: data: the decoded tensor dictionary from TfExampleDecoder. Returns: image: image tensor that is preproessed to have normalized value and dimension [output_size[0], output_size[1], 3] labels: a dictionary of tensors used for training. The following describes {key: value} pairs in the dictionary. image_info: a 2D `Tensor` that encodes the information of the image and the applied preprocessing. It is in the format of [[original_height, original_width], [scaled_height, scaled_width], anchor_boxes: ordered dictionary with keys [min_level, min_level+1, ..., max_level]. The values are tensor with shape [height_l, width_l, 4] representing anchor boxes at each level. rpn_score_targets: ordered dictionary with keys [min_level, min_level+1, ..., max_level]. The values are tensor with shape [height_l, width_l, anchors_per_location]. The height_l and width_l represent the dimension of class logits at l-th level. rpn_box_targets: ordered dictionary with keys [min_level, min_level+1, ..., max_level]. The values are tensor with shape [height_l, width_l, anchors_per_location * 4]. The height_l and width_l represent the dimension of bounding box regression output at l-th level. gt_boxes: Groundtruth bounding box annotations. The box is represented in [y1, x1, y2, x2] format. The coordinates are w.r.t the scaled image that is fed to the network. The tennsor is padded with -1 to the fixed dimension [self._max_num_instances, 4]. gt_classes: Groundtruth classes annotations. The tennsor is padded with -1 to the fixed dimension [self._max_num_instances]. gt_masks: groundtrugh masks cropped by the bounding box and resized to a fixed size determined by mask_crop_size. """ if self._use_autoaugment: try: from utils import ( autoaugment_utils, ) # pylint: disable=g-import-not-at-top except ImportError as e: logging.exception("Autoaugment is not supported in TF 2.x.") raise e classes = data["groundtruth_classes"] boxes = data["groundtruth_boxes"] masks = None attributes = None if self._include_mask: masks = data["groundtruth_instance_masks"] if self._num_attributes: attributes = data["groundtruth_attributes"] is_crowds = data["groundtruth_is_crowd"] # Skips annotations with `is_crowd` = True. if self._skip_crowd_during_training and self._is_training: num_groundtrtuhs = tf.shape(input=classes)[0] with tf.control_dependencies([num_groundtrtuhs, is_crowds]): indices = tf.cond( pred=tf.greater(tf.size(input=is_crowds), 0), true_fn=lambda: tf.compat.v1.where( tf.logical_not(is_crowds))[:, 0], false_fn=lambda: tf.cast(tf.range(num_groundtrtuhs), tf. int64), ) classes = tf.gather(classes, indices) boxes = tf.gather(boxes, indices) if self._include_mask: masks = tf.gather(masks, indices) if self._num_attributes: attributes = tf.gather(attributes, indices) # Gets original image and its size. image = data["image"] # NOTE: The autoaugment method works best when used alongside the standard # horizontal flipping of images along with size jittering and normalization. if self._use_autoaugment and not self._apply_autoaugment_after_resizing: ( image, boxes, masks, ) = autoaugment_utils.distort_image_and_masks_with_autoaugment( image, boxes, masks, self._autoaugment_policy_name) # Flips image randomly during training. if self._aug_rand_hflip: if self._include_mask: image, boxes, masks = input_utils.random_horizontal_flip( image, boxes, masks) else: image, boxes = input_utils.random_horizontal_flip(image, boxes) # Resizes and crops image. image = tf.image.convert_image_dtype(image, dtype=tf.float32) image, image_info = input_utils.resize_and_crop_image( image, self._output_size, aug_scale_min=self._aug_scale_min, aug_scale_max=self._aug_scale_max, ) # Converts boxes from normalized coordinates to pixel coordinates. # Now the coordinates of boxes are w.r.t. the original image. orig_image_shape = image_info[0] boxes = box_utils.denormalize_boxes(boxes, orig_image_shape) # Resizes and crops boxes. # Now the coordinates of boxes are w.r.t the scaled image. rescaled_image_shape = tf.shape(input=image)[:2] image_scale = image_info[2, :] offset = image_info[3, :] boxes = input_utils.resize_and_crop_boxes(boxes, image_scale, rescaled_image_shape, offset) # Filters out ground truth boxes that are all zeros. boxes, classes, masks, attributes = self._remove_empty_boxes( boxes, classes, masks, attributes) # apply the autoaugment after resizing if self._use_autoaugment and self._apply_autoaugment_after_resizing: # prepare image and boxes for the autoaugment image = tf.image.convert_image_dtype(image, dtype=tf.uint8) boxes = box_utils.normalize_boxes(boxes, rescaled_image_shape) # prepare masks for the autoaugment masks = tf.expand_dims(masks, axis=-1) scaled_mask_size = tf.cast( tf.round(orig_image_shape * image_scale), tf.int32) scaled_masks = tf.image.resize( masks, scaled_mask_size, method=tf.image.ResizeMethod.BILINEAR) offset_int = tf.cast(offset, tf.int32) masks = scaled_masks[:, offset_int[0]:offset_int[0] + rescaled_image_shape[0], offset_int[1]:offset_int[1] + rescaled_image_shape[1], ] masks = tf.squeeze(masks, axis=-1) masks = tf.cast(tf.greater(masks, 0.5), tf.float32) # apply the autoaugment ( image, boxes, masks, ) = autoaugment_utils.distort_image_and_masks_with_autoaugment( image, boxes, masks, self._autoaugment_policy_name) # convert the image back to float32 and denormalize bboxes image = tf.image.convert_image_dtype(image, dtype=tf.float32) boxes = box_utils.denormalize_boxes(boxes, rescaled_image_shape) # filters out empty bboxes boxes, classes, masks, attributes = self._remove_empty_boxes( boxes, classes, masks, attributes) if self._include_mask: if self._use_autoaugment and self._apply_autoaugment_after_resizing: # don't rescale boxes as masks were already resized cropped_boxes = box_utils.normalize_boxes( boxes, rescaled_image_shape) else: # transfer boxes to the original image space cropped_boxes = boxes + tf.tile(tf.expand_dims(offset, axis=0), [1, 2]) cropped_boxes /= tf.tile(tf.expand_dims(image_scale, axis=0), [1, 2]) cropped_boxes = box_utils.normalize_boxes( cropped_boxes, orig_image_shape) num_masks = tf.shape(input=masks)[0] masks = tf.image.crop_and_resize( tf.expand_dims(masks, axis=-1), cropped_boxes, box_indices=tf.range(num_masks, dtype=tf.int32), crop_size=[self._mask_crop_size, self._mask_crop_size], method="bilinear", ) masks = tf.squeeze(masks, axis=-1) # Normalizes image with mean and std pixel values. image = input_utils.normalize_image(image) # pad the image padded_size = input_utils.compute_padded_size(self._output_size, 2**self._max_level) image = tf.image.pad_to_bounding_box(image, 0, 0, padded_size[0], padded_size[1]) image_height, image_width, _ = image.get_shape().as_list() # Assigns anchor targets. # Note that after the target assignment, box targets are absolute pixel # offsets w.r.t. the scaled image. input_anchor = anchor.Anchor( self._min_level, self._max_level, self._num_scales, self._aspect_ratios, self._anchor_size, (image_height, image_width), ) anchor_labeler = anchor.RpnAnchorLabeler( input_anchor, self._rpn_match_threshold, self._rpn_unmatched_threshold, self._rpn_batch_size_per_im, self._rpn_fg_fraction, ) rpn_score_targets, rpn_box_targets = anchor_labeler.label_anchors( boxes, tf.cast(tf.expand_dims(classes, axis=-1), dtype=tf.float32)) # If bfloat16 is used, casts input image to tf.bfloat16. if self._use_bfloat16: image = tf.cast(image, dtype=tf.bfloat16) # Packs labels for model_fn outputs. labels = { "anchor_boxes": input_anchor.multilevel_boxes, "image_info": image_info, "rpn_score_targets": rpn_score_targets, "rpn_box_targets": rpn_box_targets, } labels["gt_boxes"] = input_utils.pad_to_fixed_size( boxes, self._max_num_instances, -1) labels["gt_classes"] = input_utils.pad_to_fixed_size( classes, self._max_num_instances, -1) if self._include_mask: labels["gt_masks"] = input_utils.pad_to_fixed_size( masks, self._max_num_instances, -1) if self._num_attributes: labels["gt_attributes"] = input_utils.pad_to_fixed_size( attributes, self._max_num_instances, -1) return image, labels