def run_inference_for_single_image(self, model, image):
image = np.asarray(image)
# The input needs to be a tensor, convert it using `tf.convert_to_tensor`.
input_tensor = tf.convert_to_tensor(image)
# The model expects a batch of images, so add an axis with `tf.newaxis`.
input_tensor = input_tensor[tf.newaxis,...]
# Run inference
model_fn = model.signatures['serving_default']
output_dict = model_fn(input_tensor)
# All outputs are batches tensors.
# Convert to numpy arrays, and take index [0] to remove the batch dimension.
# We're only interested in the first num_detections.
num_detections = int(output_dict.pop('num_detections'))
output_dict = {key:value[0, :num_detections].numpy()
for key,value in output_dict.items()}
output_dict['num_detections'] = num_detections
# detection_classes should be ints.
output_dict['detection_classes'] = output_dict['detection_classes'].astype(np.int64)
# Handle models with masks:
if 'detection_masks' in output_dict:
# Reframe the the bbox mask to the image size.
detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
output_dict['detection_masks'], output_dict['detection_boxes'],
image.shape[0], image.shape[1])
detection_masks_reframed = tf.cast(detection_masks_reframed > 0.5,
tf.uint8)
output_dict['detection_masks_reframed'] = detection_masks_reframed.numpy()
return output_dict
def run_inference_for_single_image(image, graph):
with graph.as_default():
with tf.compat.v1.Session() as sess:
# Get handles to input and output tensors
ops = tf.compat.v1.get_default_graph().get_operations()
all_tensor_names = {
output.name
for op in ops for output in op.outputs
}
tensor_dict = {}
for key in [
'num_detections', 'detection_boxes', 'detection_scores',
'detection_classes', 'detection_masks'
]:
tensor_name = key + ':0'
if tensor_name in all_tensor_names:
tensor_dict[key] = tf.compat.v1.get_default_graph(
).get_tensor_by_name(tensor_name)
if 'detection_masks' in tensor_dict:
# The following processing is only for single image
detection_boxes = tf.squeeze(tensor_dict['detection_boxes'],
[0])
detection_masks = tf.squeeze(tensor_dict['detection_masks'],
[0])
# Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
real_num_detection = tf.cast(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 = utils_ops.reframe_box_masks_to_image_masks(
detection_masks, detection_boxes, image.shape[0],
image.shape[1])
detection_masks_reframed = tf.cast(
tf.greater(detection_masks_reframed, 0.5), tf.uint8)
# Follow the convention by adding back the batch dimension
tensor_dict['detection_masks'] = tf.expand_dims(
detection_masks_reframed, 0)
image_tensor = tf.compat.v1.get_default_graph().get_tensor_by_name(
'image_tensor:0')
# Run inference
output_dict = sess.run(
tensor_dict,
feed_dict={image_tensor: np.expand_dims(image, 0)})
# all outputs are float32 numpy arrays, so convert types as appropriate
output_dict['num_detections'] = int(
output_dict['num_detections'][0])
output_dict['detection_classes'] = output_dict[
'detection_classes'][0].astype(np.uint8)
output_dict['detection_boxes'] = output_dict['detection_boxes'][0]
output_dict['detection_scores'] = output_dict['detection_scores'][
0]
if 'detection_masks' in output_dict:
output_dict['detection_masks'] = output_dict[
'detection_masks'][0]
return output_dict
def reframe_mask(self, dsize):
detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
self.detection_masks, self.detection_boxes, dsize[1], dsize[0])
detection_masks_reframed = tf.cast(
tf.greater(detection_masks_reframed, 0.5), tf.uint8)
# Follow the convention by adding back the batch dimension
self.tensor_dict['detection_masks'] = tf.expand_dims(
detection_masks_reframed, 0)
def run_inference_for_single_image(image, graph):
with graph.as_default():
with tf.compat.v1.Session() as sess:
ops = tf.compat.v1.get_default_graph().get_operations()
all_tensor_names = {
output.name
for op in ops for output in op.outputs
}
tensor_dict = {}
for key in [
'num_detections', 'detection_boxes', 'detection_scores',
'detection_classes', 'detection_masks'
]:
tensor_name = key + ':0'
if tensor_name in all_tensor_names:
tensor_dict[key] = tf.compat.v1.get_default_graph(
).get_tensor_by_name(tensor_name)
if 'detection_masks' in tensor_dict:
detection_boxes = tf.squeeze(tensor_dict['detection_boxes'],
[0])
detection_masks = tf.squeeze(tensor_dict['detection_masks'],
[0])
real_num_detection = tf.cast(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 = utils_ops.reframe_box_masks_to_image_masks(
detection_masks, detection_boxes, image.shape[0],
image.shape[1])
detection_masks_reframed = tf.cast(
tf.greater(detection_masks_reframed, 0.5), tf.uint8)
tensor_dict['detection_masks'] = tf.expand_dims(
detection_masks_reframed, 0)
image_tensor = tf.compat.v1.get_default_graph().get_tensor_by_name(
'image_tensor:0')
output_dict = sess.run(
tensor_dict,
feed_dict={image_tensor: np.expand_dims(image, 0)})
output_dict['num_detections'] = int(
output_dict['num_detections'][0])
output_dict['detection_classes'] = output_dict[
'detection_classes'][0].astype(np.uint8)
output_dict['detection_boxes'] = output_dict['detection_boxes'][0]
output_dict['detection_scores'] = output_dict['detection_scores'][
0]
if 'detection_masks' in output_dict:
output_dict['detection_masks'] = output_dict[
'detection_masks'][0]
return output_dict
def __init__(self,
model_name,
threshold=0.5,
size=(640, 480),
label_file='data/mscoco_label_map.pbtxt'):
# Initialize some variables
print("ObjectDetector('%s', '%s')" % (model_name, label_file))
self.process_this_frame = True
self.threshold = threshold
# download model
self.graph_file = model_name + '/' + self.GRAPH_FILE_NAME
if not os.path.isfile(self.graph_file):
self.download_model(model_name)
# Load a (frozen) Tensorflow model into memory.
self.detection_graph = tf.Graph()
with self.detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(self.graph_file, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
graph = self.detection_graph
ops = graph.get_operations()
all_tensor_names = {
output.name
for op in ops for output in op.outputs
}
tensor_dict = {}
for key in [
'num_detections', 'detection_boxes', 'detection_scores',
'detection_classes', 'detection_masks'
]:
tensor_name = key + ':0'
if tensor_name in all_tensor_names:
tensor_dict[key] = graph.get_tensor_by_name(tensor_name)
if 'detection_masks' in tensor_dict:
# The following processing is only for single image
detection_boxes = tf.squeeze(tensor_dict['detection_boxes'],
[0])
detection_masks = tf.squeeze(tensor_dict['detection_masks'],
[0])
# Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
real_num_detection = tf.cast(tensor_dict['num_detections'][0],
tf.int32)
self.detection_boxes = tf.slice(detection_boxes, [0, 0],
[real_num_detection, -1])
self.detection_masks = tf.slice(detection_masks, [0, 0, 0],
[real_num_detection, -1, -1])
detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
detection_masks, detection_boxes, size[1], size[0])
detection_masks_reframed = tf.cast(
tf.greater(detection_masks_reframed, 0.5), tf.uint8)
# Follow the convention by adding back the batch dimension
tensor_dict['detection_masks'] = tf.expand_dims(
detection_masks_reframed, 0)
self.tensor_dict = tensor_dict
self.sess = tf.Session(graph=self.detection_graph)
# Loading label map
# Label maps map indices to category names,
# so that when our convolution network predicts `5`,
# we know that this corresponds to `airplane`.
# Here we use internal utility functions,
# but anything that returns a dictionary mapping integers to appropriate string labels would be fine
label_map = label_map_util.load_labelmap(label_file)
categories = label_map_util.convert_label_map_to_categories(
label_map, max_num_classes=self.NUM_CLASSES, use_display_name=True)
self.category_index = label_map_util.create_category_index(categories)
np.savez_compressed('category', category=self.category_index)
self.output_dict = None
self.last_inference_time = 0
def run_inference(image, data, model_dir, graph_file):
timing_csv_file = open(FLAGS.csv_file_path, "a")
detection_graph = tf.Graph()
tfConfigParams = read_inputs()
with detection_graph.as_default():
config = tf.ConfigProto()
for key, value in tfConfigParams.items():
if (key == "inter_op_parallelism_threads"):
config.inter_op_parallelism_threads = value
if (key == "intra_op_parallelism_threads"):
config.intra_op_parallelism_threads = value
if (key == "allow_soft_placement"):
config.allow_soft_placement = value
timing_csv_buffer_data = []
with tf.Session(config=config) as sess:
with tf.gfile.GFile(os.path.join(model_dir, graph_file),
'rb') as f:
print("graph", os.path.join(model_dir, graph_file))
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
sess.graph.as_default()
tf.import_graph_def(graph_def, name='')
# Get handles to input and output tensors
ops = tf.get_default_graph().get_operations()
all_tensor_names = {
output.name
for op in ops for output in op.outputs
}
tensor_dict = {}
for key in [
'num_detections', 'detection_boxes',
'detection_scores', 'detection_classes',
'detection_masks'
]:
tensor_name = key + ':0'
if tensor_name in all_tensor_names:
tensor_dict[key] = tf.get_default_graph(
).get_tensor_by_name(tensor_name)
if 'detection_masks' in tensor_dict:
# The following processing is only for single image
detection_boxes = tf.squeeze(
tensor_dict['detection_boxes'], [0])
detection_masks = tf.squeeze(
tensor_dict['detection_masks'], [0])
# Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
real_num_detection = tf.cast(
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 = utils_ops.reframe_box_masks_to_image_masks(
detection_masks, detection_boxes, image.shape[0],
image.shape[1])
detection_masks_reframed = tf.cast(
tf.greater(detection_masks_reframed, 0.5), tf.uint8)
# Follow the convention by adding back the batch dimension
tensor_dict['detection_masks'] = tf.expand_dims(
detection_masks_reframed, 0)
image_tensor = tf.get_default_graph().get_tensor_by_name(
'image_tensor:0')
# Run inference
tf.logging.info("Starting execution")
tf.logging.info("Starting Warmup cycle")
for _ in range(_WARMUP_NUM_LOOPS):
output_dict = sess.run(tensor_dict,
feed_dict={image_tensor: image})
tf.logging.info("Starting timing.")
for iter in range(FLAGS.iterations):
tstart = time.time()
output_dict = sess.run(tensor_dict,
feed_dict={image_tensor: image})
tend = time.time()
timing_csv_buffer_data.append(
str(tstart) + "," + str(tend))
# all outputs are float32 numpy arrays, so convert types as appropriate
output_dict['num_detections'] = int(
output_dict['num_detections'][0])
output_dict['detection_classes'] = output_dict[
'detection_classes'][0].astype(np.uint8)
output_dict['detection_boxes'] = output_dict[
'detection_boxes'][0]
output_dict['detection_scores'] = output_dict[
'detection_scores'][0]
if 'detection_masks' in output_dict:
output_dict['detection_masks'] = output_dict[
'detection_masks'][0]
return timing_csv_buffer_data