def recognize_from_image(filename, det_model, rec_model, ga_model):
# prepare input data
img = load_image(filename)
logger.debug(f'input image shape: {img.shape}')
# load identities
ident_names, ident_feats = load_identities(rec_model)
img = cv2.cvtColor(img, cv2.COLOR_BGRA2BGR)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
faces = predict(img, det_model, rec_model, ga_model)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
faces = predict(img, det_model, rec_model, ga_model)
faces = face_identification(faces, ident_feats)
# plot result
res_img = draw_detection(img, faces, ident_names)
# plot result
savepath = get_savepath(args.savepath, filename)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, res_img)
def recognize_from_image():
# net initialize
net = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=args.env_id)
# input image loop
for image_path in args.input:
# prepare input data
logger.info(image_path)
img = cv2.imread(image_path)
logger.debug(f'input image shape: {img.shape}')
input_img = preprocess(img, True)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
d1, d2, d3, d4, d5, d6, d7 = net.predict(
{'input.1': input_img}
)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
d1, d2, d3, d4, d5, d6, d7 = net.predict({'input.1': input_img})
out_img = post_process(d1)
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, out_img)
logger.info('Script finished successfully.')
def recognize_from_image(filename, detector):
# prepare input data
img_0 = load_image(filename)
logger.debug(f'input image shape: {img_0.shape}')
img = cv2.cvtColor(img_0, cv2.COLOR_BGRA2BGR)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
parsing_result = detect_objects(img, detector)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
parsing_result = detect_objects(img, detector)
output_img = Image.fromarray(np.asarray(parsing_result, dtype=np.uint8))
palette = get_palette(len(CATEGORY))
output_img.putpalette(palette)
savepath = get_savepath(args.savepath, filename)
logger.info(f'saved at : {savepath}')
output_img.save(savepath)
def recognize_from_image():
estimator = GazeEstimator(args.include_iris, args.include_head_pose)
# input image loop
for image_path in args.input:
logger.info(image_path)
src_img = cv2.imread(image_path)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for _ in range(5):
start = int(round(time.time() * 1000))
img_draw = estimator.predict_and_draw(src_img, args.draw_iris,
args.draw_head_pose)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
img_draw = estimator.predict_and_draw(src_img, args.draw_iris,
args.draw_head_pose)
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, img_draw)
logger.info('Script finished successfully.')
def recognize_from_image(filenames, net):
for filename in filenames:
# prepare input data
img = load_image(filename)
logger.info(f'input image shape: {img.shape}')
img = cv2.cvtColor(img, cv2.COLOR_BGRA2RGB)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
bboxes = predict(img, net)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
bboxes = predict(img, net)
img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
res_img = draw_bbox(img, bboxes)
# plot result
savepath = get_savepath(args.savepath, filename)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, res_img)
logger.info('Script finished successfully.')
def enhance_image():
for image_path in args.input:
# prepare input data
img = cv2.imread(image_path, cv2.IMREAD_UNCHANGED)
img = cv2.resize(img, dsize=(H, W))
# net initialize
model = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=args.env_id)
upsampler = RealESRGAN(model)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
output = upsampler.enhance(img)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
output = upsampler.enhance(img)
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, output)
logger.info('Script finished successfully.')
def recognize_from_image(filename, net):
# prepare input data
img = load_image(filename)
logger.debug(f'input image shape: {img.shape}')
img = cv2.cvtColor(img, cv2.COLOR_BGRA2BGR)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
keypoints = predict(img, net)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
keypoints = predict(img, net)
"""
plot result
"""
res_img = draw_keypoints(img, keypoints)
# cv2.imwrite(args.savepath, res_img)
savepath = get_savepath(args.savepath, filename)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, res_img)
def recognize_from_video(filename, net):
capture = webcamera_utils.get_capture(args.video)
# create video writer if savepath is specified as video format
if args.savepath != SAVE_IMAGE_PATH:
f_h = int(capture.get(cv2.CAP_PROP_FRAME_HEIGHT))
f_w = int(capture.get(cv2.CAP_PROP_FRAME_WIDTH))
writer = webcamera_utils.get_writer(args.savepath, f_h, f_w)
else:
writer = None
while True:
ret, frame = capture.read()
if cv2.waitKey(1) & 0xFF == ord('q') or not ret:
break
x = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
x = preprocess(x)
preds_ailia = net.predict(x)
search_gallery(net, preds_ailia, x[0].transpose(1, 2, 0))
# save results
if writer is not None:
savepath = get_savepath(args.savepath, filename)
plt.savefig(savepath, bbox_inches='tight')
#writer.write(res_img)
plt.show()
#break
capture.release()
cv2.destroyAllWindows()
if writer is not None:
writer.release()
def recognize_from_image(filename, detector):
# load input image
img = load_image(filename)
img = cv2.cvtColor(img, cv2.COLOR_BGRA2BGR)
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
boxes, scores, cls_inds = detect_objects(img, detector)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
boxes, scores, cls_inds = detect_objects(img, detector)
try:
logger.info('\n'.join([
'pos:{}, ids:{}, score:{:.3f}'.format(
'(%.1f,%.1f,%.1f,%.1f)' % (box[0], box[1], box[2], box[3]),
COCO_CATEGORY[int(obj_cls)], score)
for box, obj_cls, score in zip(boxes, cls_inds, scores)
]))
except:
# FIXME: do not use base 'except'
pass
# show image
im2show = draw_detection(img, boxes, scores, cls_inds)
savepath = get_savepath(args.savepath, filename)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, im2show)
def recognize_from_image():
# net initialize
pose = ailia.PoseEstimator(MODEL_PATH,
WEIGHT_PATH,
env_id=args.env_id,
algorithm=ALGORITHM)
# input image loop
for image_path in args.input:
# prepare input data
logger.info(image_path)
src_img = cv2.imread(image_path)
input_image = load_image(image_path, (IMAGE_HEIGHT, IMAGE_WIDTH),
normalize_type='None')
input_data = cv2.cvtColor(input_image, cv2.COLOR_RGB2BGRA)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
_ = pose.compute(input_data)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
_ = pose.compute(input_data)
# post-processing
count = pose.get_object_count()
logger.info(f'person_count={count}')
display_result(src_img, pose)
# cv2.imwrite(args.savepath, src_img)
cv2.imwrite(get_savepath(args.savepath, image_path), src_img)
logger.info('Script finished successfully.')
def recognize_from_image(filename, net):
# prepare input data
img = load_image(filename)
#logger.info(f'input image shape: {img.shape}')
img = cv2.cvtColor(img, cv2.COLOR_BGRA2RGB)
img = preprocess(img)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
preds_ailia = net.predict(img)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
preds_ailia = net.predict(img)
#logger.info(f'output shape: {preds_ailia.shape}')
search_gallery(net, preds_ailia, filename)
savepath = get_savepath(args.savepath, filename)
plt.savefig(savepath, bbox_inches='tight')
logger.info(f'saved at : {savepath}')
def recognize_from_image():
# Input image loop
for image_path in args.input:
logger.info(image_path)
# Prepare input data.
dataset = _prepare_data(args, image_path=image_path)
# Initialize net.
net = _initialize_net(args)
# Inference
logger.info("Start inference...")
if args.benchmark:
logger.info("BENCHMARK mode")
for i in range(5):
start = int(round(time.time() * 1000))
_estimate(dataset[0], net, args)
end = int(round(time.time() * 1000))
logger.info(f"\tailia processing time {end - start} ms")
else:
depth_pred_col = _estimate(dataset[0], net, args)
filepath = get_savepath(args.savepath, image_path, ext=".png")
logger.info(f"saved at : {filepath}")
fast_depth_utils.save_image(depth_pred_col, filepath)
logger.info("Script finished successfully.")
def recognize_from_image():
# net initialize
net = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=args.env_id)
# input image loop
for image_path in args.input:
# prepare input data
logger.info(image_path)
img_input = cv2.imread(image_path)
# inference
logger.info('Start inference...')
logger.warning(
'Inference using CPU because model accuracy is low on GPU.')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(args.benchmark_count):
start = int(round(time.time() * 1000))
preds_img = gradio_wrapper_for_LSD(img_input, net)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
preds_img = gradio_wrapper_for_LSD(img_input, net)
# postprocessing
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, preds_img)
logger.info('Script finished successfully.')
def recognize_from_image(img_path, net_maskrcnn, net_root, net_pose):
# input image loop
for image_path in img_path:
# prepare input data
logger.info(image_path)
src_img = cv2.imread(image_path)
# load image for pposenet
original_img = cv2.imread(image_path)
# cast to pillow for mask r-cnn
image = Image.fromarray(original_img.copy()[:, :, ::-1])
# exec mask r-cnn
bbox_list = maskrcnn_to_image(image=image, net_maskrcnn=net_maskrcnn)
bbox_list[:, 2] = bbox_list[:, 2] - bbox_list[:, 0]
bbox_list[:, 3] = bbox_list[:, 3] - bbox_list[:, 1]
# print('bbox_list =\n', (bbox_list).astype(np.int))
# exec posenet
vis_img = posenet_to_image(original_img=original_img,
bbox_list=bbox_list,
net_root=net_root,
net_pose=net_pose)
# output image
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
cv2.imwrite(args.savepath, vis_img)
logger.info('finished process and write result to %s!' % args.savepath)
def recognize_from_image(net):
# input image loop
for image_path in args.input:
logger.info(image_path)
# prepare input data
img = load_image(image_path)
img = cv2.cvtColor(img, cv2.COLOR_BGRA2BGR)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
total_time_estimation = 0
for i in range(args.benchmark_count):
start = int(round(time.time() * 1000))
out_img = predict(net, img)
end = int(round(time.time() * 1000))
estimation_time = (end - start)
# Loggin
logger.info(f'\tailia processing estimation time {estimation_time} ms')
if i != 0:
total_time_estimation = total_time_estimation + estimation_time
logger.info(f'\taverage time estimation {total_time_estimation / (args.benchmark_count - 1)} ms')
else:
out_img = predict(net, img)
# plot result
savepath = get_savepath(args.savepath, image_path, ext='.png')
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, out_img)
logger.info('Script finished successfully.')
def recognize_from_video(detector):
capture = webcamera_utils.get_capture(args.video)
# create video writer if savepath is specified as video format
if args.savepath != SAVE_IMAGE_PATH:
f_h = int(capture.get(cv2.CAP_PROP_FRAME_HEIGHT))
f_w = int(capture.get(cv2.CAP_PROP_FRAME_WIDTH))
save_h, save_w = f_h, f_w
writer = webcamera_utils.get_writer(args.savepath, save_h, save_w)
else:
writer = None
if args.write_prediction:
frame_count = 0
frame_digit = int(
math.log10(capture.get(cv2.CAP_PROP_FRAME_COUNT)) + 1)
video_name = os.path.splitext(os.path.basename(args.video))[0]
while (True):
ret, frame = capture.read()
if (cv2.waitKey(1) & 0xFF == ord('q')) or not ret:
break
raw_img = frame
if args.detector:
detector.compute(raw_img, args.threshold, args.iou)
res_img = plot_results(detector, raw_img, COCO_CATEGORY)
detect_object = detector
else:
img, ratio = preprocess(raw_img, (HEIGHT, WIDTH))
output = detector.run(img[None, :, :, :])
predictions = postprocess(output[0], (HEIGHT, WIDTH))[0]
detect_object = predictions_to_object(predictions, raw_img, ratio,
args.iou, args.threshold)
detect_object = reverse_letterbox(
detect_object, raw_img, (raw_img.shape[0], raw_img.shape[1]))
res_img = plot_results(detect_object, raw_img, COCO_CATEGORY)
cv2.imshow('frame', res_img)
# save results
if writer is not None:
writer.write(res_img)
# write prediction
if args.write_prediction:
savepath = get_savepath(
args.savepath,
video_name,
post_fix='_%s' %
(str(frame_count).zfill(frame_digit) + '_res'),
ext='.png')
pred_file = '%s.txt' % savepath.rsplit('.', 1)[0]
write_predictions(pred_file, detect_object, frame, COCO_CATEGORY)
frame_count += 1
capture.release()
cv2.destroyAllWindows()
if writer is not None:
writer.release()
logger.info('Script finished successfully.')
def recognize_from_image(filename, net):
# prepare input data
img = load_image(filename)
logger.debug(f'input image shape: {img.shape}')
img = cv2.cvtColor(img, cv2.COLOR_BGRA2BGR)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
out_mask = predict(img, net)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
out_mask = predict(img, net)
if not args.orig_size:
img = cv2.resize(img, (IMAGE_WIDTH, IMAGE_HEIGHT))
res_img = np.ones(img.shape, np.uint8) * 255
res_img[out_mask] = img[out_mask]
# plot result
savepath = get_savepath(args.savepath, filename)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, res_img)
logger.info('Script finished successfully.')
def recognize_from_image():
# net initialize
net = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=args.env_id)
# input image loop
for image_path in args.input:
# prepare input data
logger.info(image_path)
org_img = load_image(image_path, (IMAGE_HEIGHT, IMAGE_WIDTH))
input_data = load_image(image_path, (IMAGE_HEIGHT, IMAGE_WIDTH),
normalize_type='127.5',
gen_input_ailia=True)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
preds_ailia = net.predict([input_data])
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
preds_ailia = net.predict([input_data])
# post-processing
detections = but.postprocess(preds_ailia)
# generate detections
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
for detection in detections:
but.plot_detections(org_img, detection, save_image_path=savepath)
logger.info('Script finished successfully.')
def recognize_from_image():
# Input image loop
for image_path in args.input:
logger.info(image_path)
# Prepare input data.
dataset, image = _prepare_data(args, image_path=image_path)
# Initialize net.
net = _initialize_net(args)
# Inference
logger.info("Start inference...")
if args.benchmark:
logger.info("BENCHMARK mode")
for i in range(5):
start = int(round(time.time() * 1000))
weather, prob = _estimate(dataset, net)
end = int(round(time.time() * 1000))
logger.info(f"\tailia processing time {end - start} ms")
# show result
weather, prob = _estimate(dataset, net)
logger.info(f"result : {weather} {prob}")
filepath = get_savepath(args.savepath, image_path, ext=".png")
weather_prediction_from_image_utils.save_image(
_output_text(weather, prob), image, filepath)
logger.info(f"saved at : {filepath}")
logger.info("Script finished successfully.")
def recognize_from_image():
# net initialize
net = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=args.env_id)
net.set_input_shape((1, 1, IMAGE_HEIGHT, IMAGE_WIDTH))
# input image loop
for image_path in args.input:
# prepare input data
logger.info(image_path)
img = load_img(image_path)
logger.debug(f'input image shape: {img.shape}')
(img_lab_orig, img_lab_rs) = preprocess(img)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
out = net.predict({'input.1': img_lab_rs})[0]
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
out = net.predict({'input.1': img_lab_rs})[0]
out_img = post_process(out, img_lab_orig)
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
plt.imsave(savepath, out_img)
logger.info('Script finished successfully.')
def recognize_from_image(net, params):
category = params['category']
# input image loop
for image_path in args.input:
logger.info(image_path)
# prepare input data
img = load_image(image_path)
img = cv2.cvtColor(img, cv2.COLOR_BGRA2RGB)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
pixel_labels = detect_objects(img, net, params['img_size'])
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
pixel_labels = detect_objects(img, net, params['img_size'])
output_img = Image.fromarray(np.asarray(pixel_labels, dtype=np.uint8))
# palette = get_palette(len(category))
palette = list(itertools.chain.from_iterable(category.values()))
output_img.putpalette(palette)
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
output_img.save(savepath)
def recognize_from_image(net):
# input image loop
for image_path in args.input:
# prepare input data
logger.debug(f'input image: {image_path}')
raw_img = cv2.imread(image_path)
logger.debug(f'input image shape: {raw_img.shape}')
img = crop_and_resize(raw_img, WIDTH, HEIGHT, args.arch, args.resize)
img = preprocess(img, args.arch)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
output, output_exist = net.run(img)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
output, output_exist = net.run(img)
output = postprocess(output, args.arch)
out_img = colorize(output)
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, out_img)
logger.info('Script finished successfully.')
def recognize_from_image():
# net initialize
net = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=args.env_id)
# input image loop
for image_path in args.input:
# prepare input data
logger.info(image_path)
image = craft_pytorch_utils.load_image(image_path)
logger.debug(f'input image shape: {image.shape}')
x, ratio_w, ratio_h = craft_pytorch_utils.pre_process(image)
net.set_input_shape((1, 3, x.shape[2], x.shape[3]))
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
y, _ = net.predict({'input.1': x})
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
y, _ = net.predict({'input.1': x})
img = craft_pytorch_utils.post_process(y, image, ratio_w, ratio_h)
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, img)
logger.info('Script finished successfully.')
def recognize_from_image():
# net initialize
net = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=args.env_id)
# input image loop
for image_path in args.input:
# prepare input data
logger.info(image_path)
src_img = cv2.imread(image_path)
input_data = load_image(
image_path,
(IMAGE_HEIGHT, IMAGE_WIDTH),
)
input_data = input_data[np.newaxis, :, :, :]
net.set_input_shape(input_data.shape)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
preds_ailia = net.predict(input_data)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
preds_ailia = net.predict(input_data)
# postprocessing
pred = preds_ailia.reshape((IMAGE_HEIGHT, IMAGE_WIDTH))
dst = transfer(src_img, pred)
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, dst)
logger.info('Script finished successfully.')
def transform_image():
"""Full transormation on a single image loaded from filepath in arguments.
"""
net = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=args.env_id)
# input image loop
for image_path in args.input:
# prepare input data
logger.info(image_path)
image = cv2.imread(image_path)
if args.face_recognition:
locator = FaceLocator()
else:
locator = None
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
out_image = process_frame(net, locator, image)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
out_image = process_frame(net, locator, image)
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, out_image[..., ::-1])
return True
def wavfile_input_recognition():
if args.beamdecode:
try:
from ctcdecode import CTCBeamDecoder
except ImportError:
raise ImportError("BeamCTCDecoder requires paddledecoder package.")
decoder = CTCBeamDecoder(
LABELS,
LM_PATH,
ALPHA,
BETA,
CUTOFF_TOP_N,
CUTOFF_PROB,
BEAM_WIDTH,
NUM_PROCESS,
BRANK_LABEL_INDEX,
)
# net initialize
net = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=args.env_id)
for soundf_path in args.input:
logger.info(soundf_path)
if args.ailia_audio:
wav,sr = sf.read(soundf_path)
wav = ailia.audio.resample(wav,sr,SAMPLING_RATE)
else:
wav = librosa.load(soundf_path, sr=SAMPLING_RATE)[0]
spectrogram = create_spectrogram(wav)
net.set_input_shape(spectrogram[0].shape)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for c in range(5):
start = int(round(time.time() * 1000))
preds_ailia, output_length = net.predict(spectrogram)
end = int(round(time.time() * 1000))
logger.info("\tailia processing time {} ms".format(end-start))
else:
# Deep Speech output: output_probability, output_length
preds_ailia, output_length = net.predict(spectrogram)
if args.beamdecode:
text = beam_ctc_decode(
torch.from_numpy(preds_ailia),
torch.from_numpy(output_length),
decoder,
)
else:
text = decode(preds_ailia[0], output_length)
savepath = get_savepath(args.savepath, soundf_path, ext='.txt')
logger.info(f'Results saved at : {savepath}')
with open(savepath, 'w', encoding='utf-8') as f:
f.write(text)
logger.info(f'predict sentence:\n{text}')
logger.info('Script finished successfully.')
def recognize_from_image(filename, detector, pp_net):
# prepare input data
img_0 = load_image(filename)
logger.debug(f'input image shape: {img_0.shape}')
img = cv2.cvtColor(img_0, cv2.COLOR_BGRA2RGB)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
detect_object, seg_masks = detect_objects(img, detector, pp_net)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
detect_object, seg_masks = detect_objects(img, detector, pp_net)
# plot result
res_img = plot_results(detect_object,
img_0,
CATEGORY,
segm_masks=seg_masks)
savepath = get_savepath(args.savepath, filename)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, res_img)
def transfer_to_image():
# Prepare input data
preprocess = PreProcess(config, args, face_parser_path,
face_alignment_path, face_detector_path)
source, real_A, mask_A, diff_A, crop_face = _prepare_data(
args, preprocess, "source")
_, real_B, mask_B, diff_B, _ = _prepare_data(args, preprocess, "reference")
# Net initialize
net = _initialize_net(args)
# Inference
logger.info("Start inference...")
if args.benchmark:
logger.info("BENCHMARK mode")
for i in range(5):
start = int(round(time.time() * 1000))
out = _transfer(real_A, real_B, mask_A, mask_B, diff_A, diff_B,
net)
end = int(round(time.time() * 1000))
logger.info(f"\tailia processing time {end - start} ms")
else:
out = _transfer(real_A, real_B, mask_A, mask_B, diff_A, diff_B, net)
# Postprocessing
postprocess = PostProcess(config)
image = _postprocessing(out[0], source, crop_face, postprocess)
savepath = get_savepath(args.savepath, args.input[0])
image.save(savepath)
logger.info(f"saved at : {savepath}")
logger.info("Script finished successfully.")
def unwarp_from_image():
# net initialize
bm_net = ailia.Net(BM_MODEL_PATH, BM_WEIGHT_PATH, env_id=args.env_id)
wc_net = ailia.Net(WC_MODEL_PATH, WC_WEIGHT_PATH, env_id=args.env_id)
# input image loop
for image_path in args.input:
# prepare input data
logger.info(image_path)
org_img = cv2.imread(image_path)
img = load_image(
image_path,
(WC_IMG_HEIGHT, WC_IMG_WIDTH),
normalize_type='255',
gen_input_ailia=True,
)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
uwpred = run_inference(wc_net, bm_net, img, org_img)
end = int(round(time.time() * 1000))
logger.info("\tailia processing time {} ms".format(end-start))
else:
uwpred = run_inference(wc_net, bm_net, img, org_img)
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, uwpred * 255)
logger.info('Script finished successfully.')
def recognize_from_image():
# net initialize
net = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=args.env_id)
# input image loop
for image_path in args.input:
# prepare input data
logger.info(image_path)
input_data = load_image(
image_path,
(IMAGE_HEIGHT, IMAGE_WIDTH),
normalize_type='255',
gen_input_ailia=True,
)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
preds_ailia = net.predict(input_data)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
preds_ailia = net.predict(input_data)
# postprocessing
output_img = preds_ailia[0].transpose((1, 2, 0))
output_img = cv2.cvtColor(output_img, cv2.COLOR_RGB2BGR)
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, output_img * 255)
logger.info('Script finished successfully.')