def inferenceHtptsVideo(frame,interpreter,input_tensor,session):
input_size = [int(v.strip()) for v in args.input_size.split(",")]
priors = define_img_size(input_size)
interpreter.runSession(session)
image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
image = cv2.resize(image, tuple(input_size))
image = image.astype(float)
image = (image - image_mean) / image_std
image = np.asarray(image, dtype=np.float32)
image = image.transpose((2, 0, 1))
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)
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)
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(frame.shape[1], frame.shape[0], scores, boxes, args.threshold)
tmp_face_array = []
for i in range(boxes.shape[0]):
box = boxes[i, :]
# remove to small face
min_size = 5
if ((box[3] - box[1]) < min_size and (box[2] - box[0]) > min_size)\
or ((box[3] - box[1]) > min_size and (box[2] - box[0]) < min_size)\
or ((box[3] - box[1]) < min_size and (box[2] - box[0]) < min_size):
continue
cv2.rectangle(frame, (box[0], box[1]), (box[2], box[3]), (0, 255, 0), 2)
tmp_face_array.append(frame[max(0,box[1] - 100):box[3]+100, max(0,box[0]-100):box[2]+100])
cv2.imshow("DD", cv2.resize(frame,(720,480)))
cv2.waitKey(1)
return tmp_face_array
def inferenceHtptsVideo(window_name,frame,dataset_emb,names_list,interpreter,input_tensor,session,face_net):
input_size = [int(v.strip()) for v in args.input_size.split(",")]
priors = define_img_size(input_size)
interpreter.runSession(session)
image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
image = cv2.resize(image, tuple(input_size))
image = image.astype(float)
image = (image - image_mean) / image_std
image = np.asarray(image, dtype=np.float32)
image = image.transpose((2, 0, 1))
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()
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)
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(frame.shape[1], frame.shape[0], scores, boxes, args.threshold)
files = []
all_face_results = []
for i in range(boxes.shape[0]):
box = boxes[i, :]
# remove to small face
min_size = 5
if ((box[3] - box[1]) < min_size and (box[2] - box[0]) > min_size)\
or ((box[3] - box[1]) > min_size and (box[2] - box[0]) < min_size)\
or ((box[3] - box[1]) < min_size and (box[2] - box[0]) < min_size):
continue
# up image ============
tmp_cut_face = frame[max(0,box[1] - 100):box[3]+100, max(0,box[0]-100):box[2]+100]
tmp_cut_face = cv2.resize(tmp_cut_face, (400, 500))
# cut face from image
cut_face = frame[max(0,box[1]):box[3], max(0,box[0]):box[2]]
cut_face = cv2.resize(cut_face, (160, 160))
cut_face = cut_face.reshape((1,160,160,3))
# FaceNet chrack ================================================ people / 20ms
# pred_emb = face_net.get_embedding(cut_face)
# pred_name, pred_score = compare_embadding(pred_emb, dataset_emb, names_list,0.7)
# # 在图像上绘制人脸边框和识别的结果
# show_info = [n + ':' + str(s)[:5] for n, s in zip(pred_name, pred_score)]
# all_face_results.append(pred_name[0])
# files.append(("face", np.array(cv2.imencode('.png', tmp_cut_face)[1]).tobytes()))
#
# cv2.rectangle(frame, (box[0], box[1]), (box[2], box[3]), (0, 255, 0), 2)
# cv2.putText(frame, show_info[0], (box[0], box[1]), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (255, 255, 0), 2)
# # 保存或者上传数据
# if len(files) != 0:
# # 拼接参数
# headers = {}
# payload["detectionResult"] = ",".join(all_face_results)
# print(payload)
# res = requests.request("POST", url, headers=headers, data=payload, files=files)
# print(res.text)
print("inference time: {} s".format(round(time.time() - time_time, 4)))
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 listdir:
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 = np.asarray(image, dtype=np.float32)
image = image.transpose((2, 0, 1))
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)
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)
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)
cv2.destroyAllWindows()
def inferenceHtptsVideo():
input_size = [int(v.strip()) for v in args.input_size.split(",")]
priors = define_img_size(input_size)
result_path = args.results_path
videos_path = args.videos_path
if not os.path.exists(result_path):
os.makedirs(result_path)
if not os.path.exists(result_path + "/face"):
os.makedirs(result_path + "/face")
frame_number = 0
# url = 'rtsp://*****:*****@192.168.101.107:554'
url = 'rtsp://*****:*****@192.168.2.5/Streaming/Channels/1'
cap = cv2.VideoCapture(url)
if not cap.isOpened():
print("Cannot open camera")
exit()
else:
ret, frame = cap.read()
frame_number = 0
while ret:
interpreter.runSession(session)
ret, frame = cap.read()
if not ret:
break
image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
image = cv2.resize(image, tuple(input_size))
image = image.astype(float)
image = (image - image_mean) / image_std
image = np.asarray(image, dtype=np.float32)
image = image.transpose((2, 0, 1))
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()
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)
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(frame.shape[1], frame.shape[0], scores,
boxes, args.threshold)
for i in range(boxes.shape[0]):
box = boxes[i, :]
# remove to small face
min_size = 30
if ((box[3] - box[1]) < min_size and (box[2] - box[0]) > min_size)\
or ((box[3] - box[1]) > min_size and (box[2] - box[0]) < min_size)\
or ((box[3] - box[1]) < min_size and (box[2] - box[0]) < min_size):
continue
# cut face from image
cut_face = frame[box[1]:box[3], box[0]:box[2]]
tmp_cut_face = frame[box[1] - 100:box[3] + 100,
box[0] - 100:box[2] + 100]
tmp_cut_face = cv2.resize(tmp_cut_face, (400, 500))
# save people face
# cv2.imwrite(os.path.join(result_path + "/face", str(frame_number) + ".g"), tmp_cut_face)
cut_face = cv2.resize(cut_face, (160, 160))
cut_face = cut_face.reshape((1, 160, 160, 3))
# FaceNet chrack ================================================
pred_emb = face_net.get_embedding(cut_face)
pred_name, pred_score = compare_embadding(pred_emb, dataset_emb,
names_list, 1.0)
# 在图像上绘制人脸边框和识别的结果
show_info = [
n + ':' + str(s)[:5] for n, s in zip(pred_name, pred_score)
]
# upLoad Image and Data
upDate["timestape"] = time.time()
upDate["detection_result"] = show_info[0]
upDate["image"] = np.array(cv2.imencode(
'.png', tmp_cut_face)[1]).tobytes()
res = requests.post(url=url, data=json.dumps(upDate))
print(res.text)
cv2.rectangle(frame, (box[0], box[1]), (box[2], box[3]),
(0, 255, 0), 2)
cv2.putText(frame, show_info[0], (box[0], box[1]),
cv2.FONT_HERSHEY_SIMPLEX, 0.8, (255, 255, 0), 2)
# remove no face frame
frame_number += 1
print("inference time: {} s".format(round(time.time() - time_time, 4)))
# cv2.imwrite(os.path.join(result_path, str(frame_number) + ".jpg"), frame)
# print("result_pic is written to {}".format(os.path.join(result_path, file_path)))
cv2.imshow("UltraFace_mnn", frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cv2.destroyAllWindows()
