def prepare_model(self, input_type):
"""
prepares DeepLab model
input_type: must be 'image' or 'video'
"""
assert input_type in ['image',
'video'], "only image or video input possible"
super(DeepLabModel, self).prepare_model()
self.input_type = input_type
# fixed input sizes as model needs resize either way
# Input configurations
self.category_index = None
if self.input_type is 'video':
self._input_stream = VideoStream(self.config.VIDEO_INPUT,
self.config.WIDTH,
self.config.HEIGHT).start()
elif self.input_type is 'image':
self._input_stream = ImageStream(self.config.IMAGE_PATH,
self.config.LIMIT_IMAGES).start()
if self.config.WRITE_TIMELINE:
self._run_options = tf.RunOptions(
trace_level=tf.RunOptions.FULL_TRACE)
self._run_metadata = tf.RunMetadata()
self._timeliner = TimeLiner()
print("> Building Graph")
with self.detection_graph.as_default():
with tf.Session(graph=self.detection_graph,
config=self._tf_config) as self._sess:
return self
def prepare_input_stream(self):
"""
prepares Input Stream
stream types: 'video','image','ros'
gets called by prepare model
"""
if self.input_type is 'video':
self._is_videoD = True
self._input_stream = VideoStream(self.config.VIDEO_INPUT,
self.config.WIDTH,
self.config.HEIGHT).start()
self.stream_height = self._input_stream.real_height
self.stream_width = self._input_stream.real_width
elif self.input_type is 'image':
self._is_imageD = True
self._input_stream = ImageStream(
self.config.IMAGE_PATH, self.config.LIMIT_IMAGES,
(self.config.WIDTH, self.config.HEIGHT)).start()
self.stream_height = self.config.HEIGHT
self.stream_width = self.config.WIDTH
elif self.input_type is 'ros':
self.prepare_ros('detection_node')
# Timeliner for image detection
if self.config.WRITE_TIMELINE:
self.prepare_timeliner()
def prepare_input_stream(self):
if self.input_type is 'video':
self._is_videoD = True
self._input_stream = VideoStream(self.config.VIDEO_INPUT,self.config.WIDTH,self.config.HEIGHT).start()
elif self.input_type is 'image':
self._is_imageD = True
self._input_stream = ImageStream(self.config.IMAGE_PATH,self.config.LIMIT_IMAGES).start()
if self.config.WRITE_TIMELINE:
self.prepare_timeliner()
elif self._input_type is 'ros':
self.prepare_ros('deeplab_node')
def prepare_model(self, input_type):
"""
prepares Object_Detection model
input_type: must be 'image' or 'video'
"""
assert input_type in ['image', 'video'
], "only 'image' or 'video' input possible"
super(ObjectDetectionModel, self).prepare_model()
self.input_type = input_type
# Tracker
if self.config.USE_TRACKER:
sys.path.append(os.getcwd() + '/rod/kcf')
import KCF
self._tracker = KCF.kcftracker(False, True, False, False)
self._tracker_counter = 0
self._track = False
print("> Building Graph")
with self.detection_graph.as_default():
with tf.Session(graph=self.detection_graph,
config=self._tf_config) as self._sess:
# Input Configuration
if self.input_type is 'video':
self._input_stream = VideoStream(
self.config.VIDEO_INPUT, self.config.WIDTH,
self.config.HEIGHT).start()
height = self._input_stream.real_height
width = self._input_stream.real_width
elif self.input_type is 'image':
self._input_stream = ImageStream(
self.config.IMAGE_PATH, self.config.LIMIT_IMAGES,
(self.config.WIDTH, self.config.HEIGHT)).start()
height = self.config.HEIGHT
width = self.config.WIDTH
# Timeliner for image detection
if self.config.WRITE_TIMELINE:
self._run_options = tf.RunOptions(
trace_level=tf.RunOptions.FULL_TRACE)
self._run_metadata = tf.RunMetadata()
self.timeliner = TimeLiner()
# Define Input and Ouput tensors
self._tensor_dict = self.get_tensordict([
'num_detections', 'detection_boxes', 'detection_scores',
'detection_classes', 'detection_masks'
])
self._image_tensor = self.detection_graph.get_tensor_by_name(
'image_tensor:0')
# Mask Transformations
if 'detection_masks' in self._tensor_dict:
# Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
detection_boxes = tf.squeeze(
self._tensor_dict['detection_boxes'], [0])
detection_masks = tf.squeeze(
self._tensor_dict['detection_masks'], [0])
real_num_detection = tf.cast(
self._tensor_dict['num_detections'][0], tf.int32)
detection_boxes = tf.slice(detection_boxes, [0, 0],
[real_num_detection, -1])
detection_masks = tf.slice(detection_masks, [0, 0, 0],
[real_num_detection, -1, -1])
detection_masks_reframed = reframe_box_masks_to_image_masks(
detection_masks, detection_boxes, height, width)
detection_masks_reframed = tf.cast(
tf.greater(detection_masks_reframed, 0.5), tf.uint8)
self._tensor_dict['detection_masks'] = tf.expand_dims(
detection_masks_reframed, 0)
if self.config.SPLIT_MODEL:
self._score_out = self.detection_graph.get_tensor_by_name(
'{}:0'.format(self.config.SPLIT_NODES[0]))
self._expand_out = self.detection_graph.get_tensor_by_name(
'{}:0'.format(self.config.SPLIT_NODES[1]))
self._score_in = self.detection_graph.get_tensor_by_name(
'{}_1:0'.format(self.config.SPLIT_NODES[0]))
self._expand_in = self.detection_graph.get_tensor_by_name(
'{}_1:0'.format(self.config.SPLIT_NODES[1]))
# Threading
self._gpu_worker = SessionWorker("GPU",
self.detection_graph,
self._tf_config)
self._cpu_worker = SessionWorker("CPU",
self.detection_graph,
self._tf_config)
self._gpu_opts = [self._score_out, self._expand_out]
self._cpu_opts = [
self._tensor_dict['detection_boxes'],
self._tensor_dict['detection_scores'],
self._tensor_dict['detection_classes'],
self._tensor_dict['num_detections']
]
return self