def non_interactive_demo(model, args):
renderer = create_renderer()
show_window = not args.no_show
for rec in tqdm(model.images_list):
log.info("Starting inference for %s", rec['img_name'])
image = rec['img']
distribution, targets = model.infer_sync(image)
prob = calculate_probability(distribution)
log.info("Confidence score is %s", prob)
if prob >= args.conf_thresh ** len(distribution):
phrase = model.vocab.construct_phrase(targets)
if args.output_file:
with open(args.output_file, 'a') as output_file:
output_file.write(rec['img_name'] + '\t' + phrase + '\n')
else:
print("\n\tImage name: {}\n\tFormula: {}\n".format(rec['img_name'], phrase))
if renderer is not None:
rendered_formula, _ = renderer.render(phrase)
if rendered_formula is not None and show_window:
cv.imshow("Predicted formula", rendered_formula)
cv.waitKey(0)
else:
log.info("Confidence score is low. The formula was not recognized.")
if args.perf_counts:
log.info("Encoder performance statistics")
print_stats(model.exec_net_encoder)
log.info("Decoder performance statistics")
print_stats(model.exec_net_decoder)
def calculate_class_probabilities(summaries, data):
'''
Helper function to calculate the probabilities of
each class given the current data value. This
function helps in calculating the aposteriori for
each class
Parameter
---------
summaries: the summaries of each feature calculated
while training the model on the train
dataset
data: A unit data vector, for which the class
probabilities need to be calculated
Return
------
probabilities: The aproiori probability for each
class as calculated by the standard
formaula and independent assumptions
'''
total_rows = sum([summaries[label][0][2] for label in summaries])
probabilities = dict()
for class_value, class_summaries in summaries.items():
probabilities[class_value] = summaries[class_value][0][2] / float(
total_rows)
for i in range(len(class_summaries)):
# for each class get the class summaries and store them
mean, stdev, _, _ = class_summaries[i]
# multiply by the likelihood of the data
probabilities[class_value] *= calculate_probability(
data[i], mean, stdev)
return probabilities
def main():
log.basicConfig(format="[ %(levelname)s ] %(message)s",
level=log.INFO,
stream=sys.stdout)
args = build_argparser().parse_args()
interactive_mode = not (os.path.isdir(args.input)
or args.input.endswith('.png')
or args.input.endswith('.jpg'))
model = Model(args, interactive_mode)
if not interactive_mode:
non_interactive_demo(model, args)
return
height, width = model.encoder.input_info['imgs'].input_data.shape[-2:]
prev_text = ''
demo = InteractiveDemo((height, width), resolution=args.resolution)
show_window = not args.no_show
capture = create_capture(args.input, demo.resolution)
if not capture.isOpened():
log.error("Cannot open camera")
return 1
while True:
ret, frame = capture.read()
if not ret:
log.info("End of file or error reading from camera")
break
bin_crop = demo.get_crop(frame)
model_input = prerocess_crop(bin_crop, (height, width),
preprocess_type=args.preprocessing_type)
frame = demo.put_crop(frame, model_input)
model_res = model.infer_async(model_input)
if not model_res:
phrase = prev_text
else:
distribution, targets = model_res
prob = calculate_probability(distribution)
log.info("Confidence score is %s", prob)
if prob >= args.conf_thresh**len(distribution):
log.info("Prediction updated")
phrase = model.vocab.construct_phrase(targets)
else:
log.info("Confidence score is low, prediction is not complete")
phrase = ''
frame = demo.draw(frame, phrase)
prev_text = phrase
if show_window:
cv.imshow('Press q to quit.', frame)
key = cv.waitKey(1) & 0xFF
if key in (ord('Q'), ord('q'), ord('\x1b')):
break
elif key in (ord('o'), ord('O')):
demo.resize_window("decrease")
elif key in (ord('p'), ord('P')):
demo.resize_window("increase")
log.info(
"This demo is an API example, for any performance measurements please use the dedicated benchmark_app tool "
"from the openVINO toolkit\n")
def main():
args = build_argparser().parse_args()
interactive_mode = not (os.path.isdir(args.input)
or args.input.endswith('.png')
or args.input.endswith('.jpg'))
model = Model(args, interactive_mode)
if not interactive_mode:
non_interactive_demo(model, args)
return
height, width = model.encoder.input_info['imgs'].input_data.shape[-2:]
prev_text = ''
demo = InteractiveDemo((height, width), resolution=args.resolution)
show_window = not args.no_show
capture = create_capture(args.input, demo.resolution)
if not capture.isOpened():
log.error("Cannot open camera")
return 1
while True:
ret, frame = capture.read()
if not ret:
break
bin_crop = demo.get_crop(frame)
model_input = prerocess_crop(bin_crop, (height, width),
preprocess_type=args.preprocessing_type)
frame = demo.put_crop(frame, model_input)
model_res = model.infer_async(model_input)
if not model_res:
phrase = prev_text
else:
distribution, targets = model_res
prob = calculate_probability(distribution)
log.debug("Confidence score is {}".format(prob))
if prob >= args.conf_thresh**len(distribution):
log.debug("Prediction updated")
phrase = model.vocab.construct_phrase(targets)
else:
log.debug(
"Confidence score is low, prediction is not complete")
phrase = ''
frame = demo.draw(frame, phrase)
prev_text = phrase
if show_window:
cv.imshow('Press q to quit.', frame)
key = cv.waitKey(1) & 0xFF
if key in (ord('Q'), ord('q'), ord('\x1b')):
break
elif key in (ord('o'), ord('O')):
demo.resize_window("decrease")
elif key in (ord('p'), ord('P')):
demo.resize_window("increase")
def non_interactive_demo(model, args):
renderer = create_renderer()
show_window = not args.no_show
for rec in tqdm(model.images_list):
image = rec.img
distribution, targets = model.infer_sync(image)
prob = calculate_probability(distribution)
log.info("Confidence score is {}".format(prob))
if prob >= args.conf_thresh**len(distribution):
phrase = model.vocab.construct_phrase(targets)
if args.output_file:
with open(args.output_file, 'a') as output_file:
output_file.write(rec.img_name + '\t' + phrase + '\n')
else:
print("\n\tImage name: {}\n\tFormula: {}\n".format(
rec.img_name, phrase))
if renderer is not None:
rendered_formula, _ = renderer.render(phrase)
if rendered_formula is not None and show_window:
cv.imshow("Predicted formula", rendered_formula)
cv.waitKey(0)
else:
log.info(
"Confidence score is low. The formula was not recognized.")
