Skip to content

Instantly share code, notes, and snippets.

@qmaruf
Created December 18, 2018 03:55
Show Gist options
  • Save qmaruf/1cc323cabd3c8c3505793f7b3a0f10ff to your computer and use it in GitHub Desktop.
Save qmaruf/1cc323cabd3c8c3505793f7b3a0f10ff to your computer and use it in GitHub Desktop.
def run_inference_for_multiple_images2(images, graph):
output_dicts = []
with graph.as_default():
with tf.Session() as sess:
for image in images:
# print (image)
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'
# print (tensor_name)
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:
print ('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)
tensor_dict['detection_masks'] = tf.expand_dims(detection_masks_reframed, 0)
image_tensor = tf.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)})
# print (output_dict)
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]
output_dicts.append(output_dict)
return output_dicts
image_nps = []
for image_path in TEST_IMAGE_PATHS[:5]:
image = Image.open(image_path)
image_np = load_image_into_numpy_array(image)
image_nps.append(image_np)
output_dicts = run_inference_for_multiple_images2(image_nps, detection_graph)
# print (output_dicts)
for output_dict, image_np in zip(output_dicts, image_nps):
print ('hi')
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
output_dict['detection_boxes'],
output_dict['detection_classes'],
output_dict['detection_scores'],
category_index,
instance_masks=output_dict.get('detection_masks'),
use_normalized_coordinates=True,
line_thickness=8)
plt.figure(figsize=IMAGE_SIZE)
plt.imshow(image_np)
plt.show()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment