def graph_fn(image_features): box_prediction_head = box_head.WeightSharedConvolutionalBoxHead( box_code_size) class_prediction_head = class_head.WeightSharedConvolutionalClassHead( num_classes_without_background + 1) other_heads = { other_head_name: mask_head.WeightSharedConvolutionalMaskHead( num_classes_without_background, mask_height=mask_height, mask_width=mask_width) } conv_box_predictor = box_predictor.WeightSharedConvolutionalBoxPredictor( is_training=False, num_classes=num_classes_without_background, box_prediction_head=box_prediction_head, class_prediction_head=class_prediction_head, other_heads=other_heads, conv_hyperparams_fn=self. _build_arg_scope_with_conv_hyperparams(), depth=32, num_layers_before_predictor=2) box_predictions = conv_box_predictor.predict( [image_features], num_predictions_per_location=[num_predictions_per_location], scope='BoxPredictor') for key, value in box_predictions.items(): box_predictions[key] = tf.concat(value, axis=1) assert len(box_predictions) == 3 return (box_predictions[box_predictor.BOX_ENCODINGS], box_predictions[ box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND], box_predictions[other_head_name])
def test_get_predictions_with_feature_maps_of_dynamic_shape( self): image_features = tf.placeholder(dtype=tf.float32, shape=[4, None, None, 64]) conv_box_predictor = box_predictor.WeightSharedConvolutionalBoxPredictor( is_training=False, num_classes=0, conv_hyperparams_fn=self._build_arg_scope_with_conv_hyperparams(), depth=32, num_layers_before_predictor=1, box_code_size=4) box_predictions = conv_box_predictor.predict( [image_features], num_predictions_per_location=[5], scope='BoxPredictor') box_encodings = tf.concat(box_predictions[box_predictor.BOX_ENCODINGS], axis=1) objectness_predictions = tf.concat(box_predictions[ box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND], axis=1) init_op = tf.global_variables_initializer() resolution = 32 expected_num_anchors = resolution*resolution*5 with self.test_session() as sess: sess.run(init_op) (box_encodings_shape, objectness_predictions_shape) = sess.run( [tf.shape(box_encodings), tf.shape(objectness_predictions)], feed_dict={image_features: np.random.rand(4, resolution, resolution, 64)}) self.assertAllEqual(box_encodings_shape, [4, expected_num_anchors, 4]) self.assertAllEqual(objectness_predictions_shape, [4, expected_num_anchors, 1])
def graph_fn(image_features): conv_box_predictor = box_predictor.WeightSharedConvolutionalBoxPredictor( is_training=True, num_classes=2, conv_hyperparams_fn=self._build_arg_scope_with_conv_hyperparams(), depth=32, num_layers_before_predictor=1, class_prediction_bias_init=-4.6, box_code_size=4) box_predictions = conv_box_predictor.predict( [image_features], num_predictions_per_location=[5], scope='BoxPredictor') class_predictions = tf.concat(box_predictions[ box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND], axis=1) return (tf.nn.sigmoid(class_predictions),)
def graph_fn(image_features): conv_box_predictor = box_predictor.WeightSharedConvolutionalBoxPredictor( is_training=False, num_classes=0, conv_hyperparams_fn=self._build_arg_scope_with_conv_hyperparams(), depth=32, num_layers_before_predictor=1, box_code_size=4) box_predictions = conv_box_predictor.predict( [image_features], num_predictions_per_location=[5], scope='BoxPredictor') box_encodings = tf.concat( box_predictions[box_predictor.BOX_ENCODINGS], axis=1) objectness_predictions = tf.concat(box_predictions[ box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND], axis=1) return (box_encodings, objectness_predictions)
def build_weight_shared_convolutional_box_predictor( is_training, num_classes, conv_hyperparams_fn, depth, num_layers_before_predictor, box_code_size, kernel_size=3, add_background_class=True, class_prediction_bias_init=0.0, use_dropout=False, dropout_keep_prob=0.8, share_prediction_tower=False, apply_batch_norm=True, use_depthwise=False, score_converter_fn=tf.identity, box_encodings_clip_range=None): box_prediction_head = box_head.WeightSharedConvolutionalBoxHead( box_code_size=box_code_size, kernel_size=kernel_size, use_depthwise=use_depthwise, box_encodings_clip_range=box_encodings_clip_range) class_prediction_head = ( class_head.WeightSharedConvolutionalClassHead( num_class_slots=( num_classes + 1 if add_background_class else num_classes), kernel_size=kernel_size, class_prediction_bias_init=class_prediction_bias_init, use_dropout=use_dropout, dropout_keep_prob=dropout_keep_prob, use_depthwise=use_depthwise, score_converter_fn=score_converter_fn)) other_heads = {} return convolutional_box_predictor.WeightSharedConvolutionalBoxPredictor( is_training=is_training, num_classes=num_classes, box_prediction_head=box_prediction_head, class_prediction_head=class_prediction_head, other_heads=other_heads, conv_hyperparams_fn=conv_hyperparams_fn, depth=depth, num_layers_before_predictor=num_layers_before_predictor, kernel_size=kernel_size, apply_batch_norm=apply_batch_norm, share_prediction_tower=share_prediction_tower, use_depthwise=use_depthwise)
def graph_fn(image_features1, image_features2): conv_box_predictor = box_predictor.WeightSharedConvolutionalBoxPredictor( is_training=False, num_classes=num_classes_without_background, conv_hyperparams_fn=self._build_arg_scope_with_conv_hyperparams(), depth=32, num_layers_before_predictor=2, box_code_size=4, share_prediction_tower=True) box_predictions = conv_box_predictor.predict( [image_features1, image_features2], num_predictions_per_location=[5, 5], scope='BoxPredictor') box_encodings = tf.concat( box_predictions[box_predictor.BOX_ENCODINGS], axis=1) class_predictions_with_background = tf.concat( box_predictions[box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND], axis=1) return (box_encodings, class_predictions_with_background)
def build_weight_shared_convolutional_box_predictor( is_training, num_classes, conv_hyperparams_fn, depth, num_layers_before_predictor, box_code_size, kernel_size=3, add_background_class=True, class_prediction_bias_init=0.0, use_dropout=False, dropout_keep_prob=0.8, share_prediction_tower=False, apply_batch_norm=True, use_depthwise=False, score_converter_fn=tf.identity, box_encodings_clip_range=None): """Builds and returns a WeightSharedConvolutionalBoxPredictor class. Args: is_training: Indicates whether the BoxPredictor is in training mode. num_classes: number of classes. Note that num_classes *does not* include the background category, so if groundtruth labels take values in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the assigned classification targets can range from {0,... K}). conv_hyperparams_fn: A function to generate tf-slim arg_scope with hyperparameters for convolution ops. depth: depth of conv layers. num_layers_before_predictor: Number of the additional conv layers before the predictor. box_code_size: Size of encoding for each box. kernel_size: Size of final convolution kernel. add_background_class: Whether to add an implicit background class. class_prediction_bias_init: constant value to initialize bias of the last conv2d layer before class prediction. use_dropout: Whether to apply dropout to class prediction head. dropout_keep_prob: Probability of keeping activiations. share_prediction_tower: Whether to share the multi-layer tower between box prediction and class prediction heads. apply_batch_norm: Whether to apply batch normalization to conv layers in this predictor. use_depthwise: Whether to use depthwise separable conv2d instead of conv2d. score_converter_fn: Callable score converter to perform elementwise op on class scores. box_encodings_clip_range: Min and max values for clipping the box_encodings. Returns: A WeightSharedConvolutionalBoxPredictor class. """ box_prediction_head = box_head.WeightSharedConvolutionalBoxHead( box_code_size=box_code_size, kernel_size=kernel_size, use_depthwise=use_depthwise, box_encodings_clip_range=box_encodings_clip_range) class_prediction_head = (class_head.WeightSharedConvolutionalClassHead( num_class_slots=(num_classes + 1 if add_background_class else num_classes), kernel_size=kernel_size, class_prediction_bias_init=class_prediction_bias_init, use_dropout=use_dropout, dropout_keep_prob=dropout_keep_prob, use_depthwise=use_depthwise, score_converter_fn=score_converter_fn)) other_heads = {} return convolutional_box_predictor.WeightSharedConvolutionalBoxPredictor( is_training=is_training, num_classes=num_classes, box_prediction_head=box_prediction_head, class_prediction_head=class_prediction_head, other_heads=other_heads, conv_hyperparams_fn=conv_hyperparams_fn, depth=depth, num_layers_before_predictor=num_layers_before_predictor, kernel_size=kernel_size, apply_batch_norm=apply_batch_norm, share_prediction_tower=share_prediction_tower, use_depthwise=use_depthwise)
def build(argscope_fn, box_predictor_config, is_training, num_classes): """Builds box predictor based on the configuration. Builds box predictor based on the configuration. See box_predictor.proto for configurable options. Also, see box_predictor.py for more details. Args: argscope_fn: A function that takes the following inputs: * hyperparams_pb2.Hyperparams proto * a boolean indicating if the model is in training mode. and returns a tf slim argscope for Conv and FC hyperparameters. box_predictor_config: box_predictor_pb2.BoxPredictor proto containing configuration. is_training: Whether the models is in training mode. num_classes: Number of classes to predict. Returns: box_predictor: box_predictor.BoxPredictor object. Raises: ValueError: On unknown box predictor. """ if not isinstance(box_predictor_config, box_predictor_pb2.BoxPredictor): raise ValueError('box_predictor_config not of type ' 'box_predictor_pb2.BoxPredictor.') box_predictor_oneof = box_predictor_config.WhichOneof( 'box_predictor_oneof') if box_predictor_oneof == 'convolutional_box_predictor': config_box_predictor = box_predictor_config.convolutional_box_predictor conv_hyperparams_fn = argscope_fn( config_box_predictor.conv_hyperparams, is_training) box_predictor_object = ( convolutional_box_predictor.ConvolutionalBoxPredictor( is_training=is_training, num_classes=num_classes, conv_hyperparams_fn=conv_hyperparams_fn, min_depth=config_box_predictor.min_depth, max_depth=config_box_predictor.max_depth, num_layers_before_predictor=( config_box_predictor.num_layers_before_predictor), use_dropout=config_box_predictor.use_dropout, dropout_keep_prob=config_box_predictor. dropout_keep_probability, kernel_size=config_box_predictor.kernel_size, box_code_size=config_box_predictor.box_code_size, apply_sigmoid_to_scores=config_box_predictor. apply_sigmoid_to_scores, class_prediction_bias_init=( config_box_predictor.class_prediction_bias_init), use_depthwise=config_box_predictor.use_depthwise)) return box_predictor_object if box_predictor_oneof == 'weight_shared_convolutional_box_predictor': config_box_predictor = ( box_predictor_config.weight_shared_convolutional_box_predictor) conv_hyperparams_fn = argscope_fn( config_box_predictor.conv_hyperparams, is_training) apply_batch_norm = config_box_predictor.conv_hyperparams.HasField( 'batch_norm') box_predictor_object = ( convolutional_box_predictor.WeightSharedConvolutionalBoxPredictor( is_training=is_training, num_classes=num_classes, conv_hyperparams_fn=conv_hyperparams_fn, depth=config_box_predictor.depth, num_layers_before_predictor=( config_box_predictor.num_layers_before_predictor), kernel_size=config_box_predictor.kernel_size, box_code_size=config_box_predictor.box_code_size, class_prediction_bias_init=config_box_predictor. class_prediction_bias_init, use_dropout=config_box_predictor.use_dropout, dropout_keep_prob=config_box_predictor. dropout_keep_probability, share_prediction_tower=config_box_predictor. share_prediction_tower, apply_batch_norm=apply_batch_norm)) return box_predictor_object if box_predictor_oneof == 'mask_rcnn_box_predictor': config_box_predictor = box_predictor_config.mask_rcnn_box_predictor fc_hyperparams_fn = argscope_fn(config_box_predictor.fc_hyperparams, is_training) conv_hyperparams_fn = None if config_box_predictor.HasField('conv_hyperparams'): conv_hyperparams_fn = argscope_fn( config_box_predictor.conv_hyperparams, is_training) box_prediction_head = box_head.BoxHead( is_training=is_training, num_classes=num_classes, fc_hyperparams_fn=fc_hyperparams_fn, use_dropout=config_box_predictor.use_dropout, dropout_keep_prob=config_box_predictor.dropout_keep_probability, box_code_size=config_box_predictor.box_code_size, share_box_across_classes=( config_box_predictor.share_box_across_classes)) class_prediction_head = class_head.ClassHead( is_training=is_training, num_classes=num_classes, fc_hyperparams_fn=fc_hyperparams_fn, use_dropout=config_box_predictor.use_dropout, dropout_keep_prob=config_box_predictor.dropout_keep_probability) third_stage_heads = {} if config_box_predictor.predict_instance_masks: third_stage_heads[ mask_rcnn_box_predictor.MASK_PREDICTIONS] = mask_head.MaskHead( num_classes=num_classes, conv_hyperparams_fn=conv_hyperparams_fn, mask_height=config_box_predictor.mask_height, mask_width=config_box_predictor.mask_width, mask_prediction_num_conv_layers=( config_box_predictor.mask_prediction_num_conv_layers), mask_prediction_conv_depth=( config_box_predictor.mask_prediction_conv_depth), masks_are_class_agnostic=( config_box_predictor.masks_are_class_agnostic)) box_predictor_object = mask_rcnn_box_predictor.MaskRCNNBoxPredictor( is_training=is_training, num_classes=num_classes, box_prediction_head=box_prediction_head, class_prediction_head=class_prediction_head, third_stage_heads=third_stage_heads) return box_predictor_object if box_predictor_oneof == 'rfcn_box_predictor': config_box_predictor = box_predictor_config.rfcn_box_predictor conv_hyperparams_fn = argscope_fn( config_box_predictor.conv_hyperparams, is_training) box_predictor_object = rfcn_box_predictor.RfcnBoxPredictor( is_training=is_training, num_classes=num_classes, conv_hyperparams_fn=conv_hyperparams_fn, crop_size=[ config_box_predictor.crop_height, config_box_predictor.crop_width ], num_spatial_bins=[ config_box_predictor.num_spatial_bins_height, config_box_predictor.num_spatial_bins_width ], depth=config_box_predictor.depth, box_code_size=config_box_predictor.box_code_size) return box_predictor_object raise ValueError('Unknown box predictor: {}'.format(box_predictor_oneof))
def build_weight_shared_convolutional_box_predictor( is_training, num_classes, conv_hyperparams_fn, depth, num_layers_before_predictor, box_code_size, kernel_size=3, class_prediction_bias_init=0.0, use_dropout=False, dropout_keep_prob=0.8, share_prediction_tower=False, apply_batch_norm=True, predict_instance_masks=False, mask_height=7, mask_width=7, masks_are_class_agnostic=False): """Builds and returns a WeightSharedConvolutionalBoxPredictor class. Args: is_training: Indicates whether the BoxPredictor is in training mode. num_classes: number of classes. Note that num_classes *does not* include the background category, so if groundtruth labels take values in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the assigned classification targets can range from {0,... K}). conv_hyperparams_fn: A function to generate tf-slim arg_scope with hyperparameters for convolution ops. depth: depth of conv layers. num_layers_before_predictor: Number of the additional conv layers before the predictor. box_code_size: Size of encoding for each box. kernel_size: Size of final convolution kernel. class_prediction_bias_init: constant value to initialize bias of the last conv2d layer before class prediction. use_dropout: Whether to apply dropout to class prediction head. dropout_keep_prob: Probability of keeping activiations. share_prediction_tower: Whether to share the multi-layer tower between box prediction and class prediction heads. apply_batch_norm: Whether to apply batch normalization to conv layers in this predictor. predict_instance_masks: If True, will add a third stage mask prediction to the returned class. mask_height: Desired output mask height. The default value is 7. mask_width: Desired output mask width. The default value is 7. masks_are_class_agnostic: Boolean determining if the mask-head is class-agnostic or not. Returns: A WeightSharedConvolutionalBoxPredictor class. """ box_prediction_head = box_head.WeightSharedConvolutionalBoxHead( box_code_size=box_code_size, kernel_size=kernel_size, class_prediction_bias_init=class_prediction_bias_init) class_prediction_head = (class_head.WeightSharedConvolutionalClassHead( num_classes=num_classes, kernel_size=kernel_size, class_prediction_bias_init=class_prediction_bias_init, use_dropout=use_dropout, dropout_keep_prob=dropout_keep_prob)) other_heads = {} if predict_instance_masks: other_heads[convolutional_box_predictor.MASK_PREDICTIONS] = ( mask_head.WeightSharedConvolutionalMaskHead( num_classes=num_classes, kernel_size=kernel_size, use_dropout=use_dropout, dropout_keep_prob=dropout_keep_prob, mask_height=mask_height, mask_width=mask_width, masks_are_class_agnostic=masks_are_class_agnostic)) return convolutional_box_predictor.WeightSharedConvolutionalBoxPredictor( is_training=is_training, num_classes=num_classes, box_prediction_head=box_prediction_head, class_prediction_head=class_prediction_head, other_heads=other_heads, conv_hyperparams_fn=conv_hyperparams_fn, depth=depth, num_layers_before_predictor=num_layers_before_predictor, kernel_size=kernel_size, apply_batch_norm=apply_batch_norm, share_prediction_tower=share_prediction_tower)