def inference():
input_size = [int(v.strip()) for v in args.input_size.split(",")]
priors = define_img_size(input_size)
result_path = args.results_path
imgs_path = args.imgs_path
if not os.path.exists(result_path):
os.makedirs(result_path)
listdir = os.listdir(imgs_path)
for file_path in tqdm(listdir):
try:
img_path = os.path.join(imgs_path, file_path)
image_ori = cv2.imread(img_path)
interpreter = MNN.Interpreter(args.model_path)
session = interpreter.createSession()
input_tensor = interpreter.getSessionInput(session)
image = cv2.cvtColor(image_ori, cv2.COLOR_BGR2RGB)
image = cv2.resize(image, tuple(input_size))
image = image.astype(float)
image = (image - image_mean) / image_std
image = image.transpose((2, 0, 1))
image = image.astype(np.float32)
tmp_input = MNN.Tensor((1, 3, input_size[1], input_size[0]),
MNN.Halide_Type_Float, image,
MNN.Tensor_DimensionType_Caffe)
input_tensor.copyFrom(tmp_input)
time_time = time.time()
interpreter.runSession(session)
scores = interpreter.getSessionOutput(session, "scores").getData()
boxes = interpreter.getSessionOutput(session, "boxes").getData()
boxes = np.expand_dims(np.reshape(boxes, (-1, 4)), axis=0)
scores = np.expand_dims(np.reshape(scores, (-1, 2)), axis=0)
print("inference time: {} s".format(
round(time.time() - time_time, 4)))
boxes = box_utils.convert_locations_to_boxes(
boxes, priors, center_variance, size_variance)
boxes = box_utils.center_form_to_corner_form(boxes)
boxes, labels, probs = predict(image_ori.shape[1],
image_ori.shape[0], scores, boxes,
args.threshold)
if boxes.shape[0] > 0:
for i in range(boxes.shape[0]):
box = boxes[i, :]
cv2.rectangle(image_ori, (box[0], box[1]),
(box[2], box[3]), (0, 255, 0), 2)
label = labels[i]
result_path_label = os.path.join(result_path, str(label))
if not os.path.exists(result_path_label):
os.makedirs(result_path_label)
cv2.imwrite(os.path.join(result_path_label, file_path),
image_ori)
# cv2.imwrite(os.path.join(result_path, file_path), image_ori)
print("result_pic is written to {}".format(
os.path.join(result_path, file_path)))
# cv2.imshow("UltraFace_mnn_py", image_ori)
# cv2.waitKey(-1)
except Exception as e:
print(e)
image = cv2.cvtColor(orig_image, cv2.COLOR_BGR2RGB)
#image = cv2.resize(image, (320, 240))
image = cv2.resize(image, (640, 480))
image_mean = np.array([127, 127, 127])
image = (image - image_mean) / 128
image = np.transpose(image, [2, 0, 1])
image = np.expand_dims(image, axis=0)
image = image.astype(np.float32)
# confidences, boxes = predictor.run(image)
time_time = time.time()
confidences, boxes = ort_session.run(None, {input_name: image})
############
boxes = box_utils.convert_locations_to_boxes(
boxes, fd_config.priors, fd_config.center_variance,
fd_config.size_variance
#torch.from_numpy(boxes), fd_config.priors, fd_config.center_variance, fd_config.size_variance
)
boxes = box_utils.center_form_to_corner_form(boxes)
############
print("cost time:{}".format(time.time() - time_time))
boxes, labels, probs = predict(orig_image.shape[1], orig_image.shape[0],
confidences, boxes, threshold)
for i in range(boxes.shape[0]):
box = boxes[i, :]
label = f"{class_names[labels[i]]}: {probs[i]:.2f}"
color = random.choice(colors)
c1 = (box[0], box[1])
for file_path in listdir:
img_path = os.path.join(path, file_path)
time_time = time.time()
orig_image = cv2.imread(img_path)
image = cv2.cvtColor(orig_image, cv2.COLOR_BGR2RGB)
image = cv2.resize(image, (320, 240))
# image = cv2.resize(image, (640, 480))
image_mean = np.array([127, 127, 127])
image = (image - image_mean) / 128
image = np.transpose(image, [2, 0, 1])
image = np.expand_dims(image, axis=0)
image = image.astype(np.float32)
confidences, locations = ort_session.run(None, {input_name: image})
# print(locations)
boxes = box_utils.convert_locations_to_boxes(locations,
config.priors.to('cpu'),
config.center_variance,
config.size_variance)
boxes = box_utils.center_form_to_corner_form(boxes)
boxes, labels, probs = predict(orig_image.shape[1], orig_image.shape[0],
confidences, boxes, threshold)
print("FPS:{}".format(1 / (time.time() - time_time)))
for i in range(boxes.shape[0]):
box = boxes[i, :]
label = f"{class_names[labels[i]]}: {probs[i]:.2f}"
cv2.rectangle(orig_image, (box[0], box[1]), (box[2], box[3]),
(255, 255, 0), 4)
cv2.putText(
orig_image,