def load_and_run_detector(model_file, image_file_names, output_dir,
render_confidence_threshold=TFDetector.DEFAULT_RENDERING_CONFIDENCE_THRESHOLD,
crop_images=False):
"""Load and run detector on target images, and visualize the results."""
if len(image_file_names) == 0:
print('Warning: no files available')
return
start_time = time.time()
tf_detector = TFDetector(model_file)
elapsed = time.time() - start_time
print('Loaded model in {}'.format(humanfriendly.format_timespan(elapsed)))
detection_results = []
time_load = []
time_infer = []
# Dictionary mapping output file names to a collision-avoidance count.
#
# Since we'll be writing a bunch of files to the same folder, we rename
# as necessary to avoid collisions.
output_filename_collision_counts = {}
def input_file_to_detection_file(fn, crop_index=-1):
"""Creates unique file names for output files.
This function does 3 things:
1) If the --crop flag is used, then each input image may produce several output
crops. For example, if foo.jpg has 3 detections, then this function should
get called 3 times, with crop_index taking on 0, 1, then 2. Each time, this
function appends crop_index to the filename, resulting in
foo_crop00_detections.jpg
foo_crop01_detections.jpg
foo_crop02_detections.jpg
2) If the --recursive flag is used, then the same file (base)name may appear
multiple times. However, we output into a single flat folder. To avoid
filename collisions, we prepend an integer prefix to duplicate filenames:
foo_crop00_detections.jpg
0000_foo_crop00_detections.jpg
0001_foo_crop00_detections.jpg
3) Prepends the output directory:
out_dir/foo_crop00_detections.jpg
Args:
fn: str, filename
crop_index: int, crop number
Returns: output file path
"""
fn = os.path.basename(fn).lower()
name, ext = os.path.splitext(fn)
if crop_index >= 0:
name += '_crop{:0>2d}'.format(crop_index)
fn = '{}{}{}'.format(name, ImagePathUtils.DETECTION_FILENAME_INSERT, '.jpg')
if fn in output_filename_collision_counts:
n_collisions = output_filename_collision_counts[fn]
fn = '{:0>4d}'.format(n_collisions) + '_' + fn
output_filename_collision_counts[fn] += 1
else:
output_filename_collision_counts[fn] = 0
fn = os.path.join(output_dir, fn)
return fn
for im_file in tqdm(image_file_names):
try:
start_time = time.time()
image = viz_utils.load_image(im_file)
elapsed = time.time() - start_time
time_load.append(elapsed)
except Exception as e:
print('Image {} cannot be loaded. Exception: {}'.format(im_file, e))
result = {
'file': im_file,
'failure': TFDetector.FAILURE_IMAGE_OPEN
}
detection_results.append(result)
continue
try:
start_time = time.time()
result = tf_detector.generate_detections_one_image(image, im_file)
detection_results.append(result)
elapsed = time.time() - start_time
time_infer.append(elapsed)
except Exception as e:
print('An error occurred while running the detector on image {}. Exception: {}'.format(im_file, e))
continue
try:
if crop_images:
images_cropped = viz_utils.crop_image(result['detections'], image)
for i_crop, cropped_image in enumerate(images_cropped):
output_full_path = input_file_to_detection_file(im_file, i_crop)
cropped_image.save(output_full_path)
else:
# image is modified in place
viz_utils.render_detection_bounding_boxes(result['detections'], image,
label_map=TFDetector.DEFAULT_DETECTOR_LABEL_MAP,
confidence_threshold=render_confidence_threshold)
output_full_path = input_file_to_detection_file(im_file)
image.save(output_full_path)
except Exception as e:
print('Visualizing results on the image {} failed. Exception: {}'.format(im_file, e))
continue
# ...for each image
ave_time_load = statistics.mean(time_load)
ave_time_infer = statistics.mean(time_infer)
if len(time_load) > 1 and len(time_infer) > 1:
std_dev_time_load = humanfriendly.format_timespan(statistics.stdev(time_load))
std_dev_time_infer = humanfriendly.format_timespan(statistics.stdev(time_infer))
else:
std_dev_time_load = 'not available'
std_dev_time_infer = 'not available'
print('On average, for each image,')
print('- loading took {}, std dev is {}'.format(humanfriendly.format_timespan(ave_time_load),
std_dev_time_load))
print('- inference took {}, std dev is {}'.format(humanfriendly.format_timespan(ave_time_infer),
std_dev_time_infer))
def load_and_run_detector(model_file,
image_file_names,
output_dir,
render_confidence_threshold=TFDetector.
DEFAULT_RENDERING_CONFIDENCE_THRESHOLD,
crop_images=False):
if len(image_file_names) == 0:
print('Warning: no files available')
return
# load and run detector on target images, and visualize the results
start_time = time.time()
tf_detector = TFDetector(model_file)
elapsed = time.time() - start_time
print('Loaded model in {}'.format(humanfriendly.format_timespan(elapsed)))
detection_results = []
time_load = []
time_infer = []
# Dictionary mapping output file names to a collision-avoidance count.
#
# Since we'll be writing a bunch of files to the same folder, we rename
# as necessary to avoid collisions.
output_filename_collision_counts = {}
def input_file_to_detection_file(fn, crop_index=-1):
"""
Append "_detctions" to fn, prepend the output folder.
Because we may be mapping many directories to one, we can have filename
collisions. Resolve by adding integer suffixes for duplicate filenames.
"""
fn = os.path.basename(fn).lower()
name, ext = os.path.splitext(fn)
if crop_index >= 0:
name += '_crop{:0>2d}'.format(crop_index)
fn = '{}{}{}'.format(name, ImagePathUtils.DETECTION_FILENAME_INSERT,
'.jpg')
if fn in output_filename_collision_counts:
n_collisions = output_filename_collision_counts[fn]
fn = '{:0>4d}'.format(n_collisions) + '_' + fn
output_filename_collision_counts[fn] = n_collisions + 1
else:
output_filename_collision_counts[fn] = 0
fn = os.path.join(output_dir, fn)
return fn
for im_file in tqdm(image_file_names):
try:
start_time = time.time()
image = viz_utils.load_image(im_file)
elapsed = time.time() - start_time
time_load.append(elapsed)
except Exception as e:
print('Image {} cannot be loaded. Exception: {}'.format(
im_file, e))
result = {
'file': im_file,
'failure': TFDetector.FAILURE_IMAGE_OPEN
}
detection_results.append(result)
continue
try:
start_time = time.time()
result = tf_detector.generate_detections_one_image(image, im_file)
detection_results.append(result)
elapsed = time.time() - start_time
time_infer.append(elapsed)
except Exception as e:
print(
'An error occurred while running the detector on image {}. Exception: {}'
.format(im_file, e))
continue
try:
if crop_images:
images_cropped = viz_utils.crop_image(result['detections'],
image)
for i_crop, cropped_image in enumerate(images_cropped):
output_full_path = input_file_to_detection_file(
im_file, i_crop)
cropped_image.save(output_full_path)
else:
# image is modified in place
viz_utils.render_detection_bounding_boxes(
result['detections'],
image,
label_map=TFDetector.DEFAULT_DETECTOR_LABEL_MAP,
confidence_threshold=render_confidence_threshold)
output_full_path = input_file_to_detection_file(im_file)
image.save(output_full_path)
except Exception as e:
print('Visualizing results on the image {} failed. Exception: {}'.
format(im_file, e))
continue
# ...for each image
ave_time_load = statistics.mean(time_load)
ave_time_infer = statistics.mean(time_infer)
if len(time_load) > 1 and len(time_infer) > 1:
std_dev_time_load = humanfriendly.format_timespan(
statistics.stdev(time_load))
std_dev_time_infer = humanfriendly.format_timespan(
statistics.stdev(time_infer))
else:
std_dev_time_load = 'not available'
std_dev_time_infer = 'not available'
print('On average, for each image,')
print('- loading took {}, std dev is {}'.format(
humanfriendly.format_timespan(ave_time_load), std_dev_time_load))
print('- inference took {}, std dev is {}'.format(
humanfriendly.format_timespan(ave_time_infer), std_dev_time_infer))
