classes_path = 'data/coco_classes.txt'
# model_path可以是'yolov4.h5'、'./weights/step00001000.h5'这些。
# model_path = 'yolov4.h5'
model_path = './weights/step00001000.h5'
# input_shape越大，精度会上升，但速度会下降。
# input_shape = (320, 320)
input_shape = (416, 416)
# input_shape = (608, 608)
num_anchors = 3
all_classes = get_classes(classes_path)
num_classes = len(all_classes)
inputs = layers.Input(shape=(None, None, 3))
yolo = YOLOv4(inputs, num_classes, num_anchors)
yolo.load_weights(model_path, by_name=True)
_decode = Decode(0.05, 0.45, input_shape, yolo, all_classes)
# detect images in test floder.
for (root, dirs, files) in os.walk('images/test'):
if files:
start = time.time()
for f in files:
path = os.path.join(root, f)
image = cv2.imread(path)
image, boxes, scores, classes = _decode.detect_image(
image, draw_image=True)
cv2.imwrite('images/res/' + f, image)
print('total time: {0:.6f}s'.format(time.time() - start))
from model.decode_np import Decode
if __name__ == '__main__':
file = 'data/coco_classes.txt'
model_path = 'yolo_bgr_mAP_46.h5'
# input_shape越大，精度会上升，但速度会下降。
# input_shape = (320, 320)
input_shape = (416, 416)
# input_shape = (608, 608)
_decode = Decode(0.6, 0.5, input_shape, model_path, file)
# detect images in test floder.
for (root, dirs, files) in os.walk('images/test'):
if files:
start = time.time()
for f in files:
# print(f)
path = os.path.join(root, f)
image = cv2.imread(path)
image = _decode.detect_image(image)
cv2.imwrite('images/res/' + f, image)
print('total time: {0:.6f}s'.format(time.time() - start))
# detect videos one at a time in videos/test folder
# video = 'library1.mp4'
# _decode.detect_video(video)
if cv2.waitKey(1) == ord('q'):
capture.release()
cv2.destroyWindow("screen_title2")
t1 = threading.Thread(target=job1)
#t2 = threading.Thread(target = job2)
t1.start()
#t2.start()
while True:
if a > 0:
bgr_image = frame1
gray_image = cv2.cvtColor(bgr_image, cv2.COLOR_BGR2GRAY)
rgb_image = cv2.cvtColor(bgr_image, cv2.COLOR_BGR2RGB)
faces = face_detector.detect_image(bgr_image)[1]
if faces is None:
faces = ()
for face_coordinates in faces:
x1, y1, x2, y2 = face_coordinates
face_coordinates = [int(x1), int(y1), int(x2 - x1), int(y2 - y1)]
x1, x2, y1, y2 = apply_offsets(face_coordinates, emotion_offsets)
gray_face = gray_image[y1:y2, x1:x2]
try:
gray_face = cv2.resize(gray_face, (emotion_target_size))
except:
continue
gray_face = preprocess_input(gray_face, True)
gray_face = np.expand_dims(gray_face, 0)
if torch.cuda.is_available(): # 如果有gpu可用，模型（包括了权重weight）存放在gpu显存里
yolo = yolo.cuda()
yolo.load_state_dict(torch.load(model_path))
yolo.eval(
) # 必须调用model.eval()来设置dropout和batch normalization layers在运行推理前，切换到评估模式. 不这样做的化会产生不一致的推理结果.
_decode = Decode(conf_thresh, nms_thresh, input_shape, yolo, all_classes)
if not os.path.exists('images/res/'): os.mkdir('images/res/')
path_dir = os.listdir('images/test')
# warm up
if use_gpu:
for k, filename in enumerate(path_dir):
image = cv2.imread('images/test/' + filename)
image, boxes, scores, classes = _decode.detect_image(
image, draw_image=False)
if k == 10:
break
time_stat = deque(maxlen=20)
start_time = time.time()
end_time = time.time()
num_imgs = len(path_dir)
start = time.time()
for k, filename in enumerate(path_dir):
image = cv2.imread('images/test/' + filename)
image, boxes, scores, classes = _decode.detect_image(image, draw_image)
# 估计剩余时间
start_time = end_time
end_time = time.time()
place = fluid.CUDAPlace(gpu_id) if use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(startup_prog)
fluid.load(eval_prog, model_path, executor=exe)
_decode = Decode(conf_thresh, nms_thresh, input_shape, exe, eval_prog,
all_classes)
if not os.path.exists('images/res/'): os.mkdir('images/res/')
path_dir = os.listdir('images/test')
# warm up
if use_gpu:
for k, filename in enumerate(path_dir):
image = cv2.imread('images/test/' + filename)
image, boxes, scores, classes = _decode.detect_image(
image, eval_fetch_list, draw_image=False)
if k == 10:
break
time_stat = deque(maxlen=20)
start_time = time.time()
end_time = time.time()
num_imgs = len(path_dir)
start = time.time()
for k, filename in enumerate(path_dir):
image = cv2.imread('images/test/' + filename)
image, boxes, scores, classes = _decode.detect_image(
image, eval_fetch_list, draw_image)
# 估计剩余时间
start_time = end_time
class face_detect():
def __init__(self):
# hyper-parameters for bounding boxes shape
self.frame_window = 10
self.emotion_offsets = (20, 40)
# loading models
self.face_detector = Decode('data/voc_classes.txt',
'./weights/best_model.h5')
self.emotion_classifier = load_model(
'model/fer2013_mini_XCEPTION.102-0.66.hdf5', compile=False)
self.emotion_labels = get_labels('fer2013')
# getting input model shapes for inference
self.emotion_target_size = self.emotion_classifier.input_shape[1:3]
# starting lists for calculating modes
self.emotion_window = []
def faceDetect(self, bgr_image):
faces = self.face_detector.detect_image(bgr_image)[1]
probability = [0, 0, 0, 0, 0, 0, 0]
if faces is not None and len(faces) == 1:
bgr_image, probability = self.emo_Detect(bgr_image, faces[0])
return bgr_image, probability
def emo_Detect(self, bgr_image, face_coordinates):
gray_image = cv2.cvtColor(bgr_image, cv2.COLOR_BGR2GRAY)
x1, y1, x2, y2 = face_coordinates
face_coordinates = [int(x1), int(y1), int(x2 - x1), int(y2 - y1)]
x1, x2, y1, y2 = apply_offsets(face_coordinates, self.emotion_offsets)
gray_face = gray_image[y1:y2, x1:x2]
gray_face = cv2.resize(gray_face, (self.emotion_target_size))
gray_face = preprocess_input(gray_face, True)
gray_face = np.expand_dims(gray_face, 0)
gray_face = np.expand_dims(gray_face, -1)
emotion_prediction = self.emotion_classifier.predict(gray_face)
for idx, probability in enumerate(emotion_prediction[0]):
print(self.emotion_labels[idx], probability)
emotion_probability = np.max(emotion_prediction)
emotion_label_arg = np.argmax(emotion_prediction)
emotion_text = self.emotion_labels[emotion_label_arg]
self.emotion_window.append(emotion_text)
if len(self.emotion_window) > self.frame_window:
self.emotion_window.pop(0)
try:
emotion_mode = mode(self.emotion_window)
print("mode is " + emotion_mode)
except:
pass
if emotion_text == 'angry':
color = emotion_probability * np.asarray((0, 0, 255))
elif emotion_text == 'sad':
color = emotion_probability * np.asarray((255, 0, 0))
elif emotion_text == 'happy':
color = emotion_probability * np.asarray((0, 255, 255))
elif emotion_text == 'surprise':
color = emotion_probability * np.asarray((255, 255, 0))
else:
color = emotion_probability * np.asarray((0, 255, 0))
color = color.astype(int)
color = color.tolist()
draw_bounding_box(face_coordinates, bgr_image, color)
draw_text(face_coordinates, bgr_image, emotion_text, color, 0, -45, 1,
1)
return bgr_image, emotion_prediction[0]
key_list = list(test_dic.keys())
key_len = len(key_list)
while key_len == 0:
time.sleep(0.01)
key_list = list(test_dic.keys())
key_len = len(key_list)
dic = test_dic['%.8d' % 0]
image = dic['image']
pimage = dic['pimage']
im_info = dic['im_info']
# warm up
if use_gpu:
for k in range(10):
image, boxes, scores, classes = _decode.detect_image(image, pimage, im_info, draw_image=False)
time_stat = deque(maxlen=20)
start_time = time.time()
end_time = time.time()
num_imgs = len(path_dir)
start = time.time()
for k, filename in enumerate(path_dir):
key_list = list(test_dic.keys())
key_len = len(key_list)
while key_len == 0:
time.sleep(0.01)
key_list = list(test_dic.keys())
key_len = len(key_list)
dic = test_dic.pop('%.8d' % k)
def job1():
global count1
global frame
use_gpu = True
# 显存分配。
if use_gpu:
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
else:
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
from keras.backend.tensorflow_backend import set_session
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.8
set_session(tf.Session(config=config))
facesDetect = {'classes_path': 'data/voc_classes.txt', 'model_path': './weights/best_model.h5'}
emotion_model_path = 'model/fer2013_mini_XCEPTION.102-0.66.hdf5'
emotion_labels = get_labels('fer2013')
# hyper-parameters for bounding boxes shape
frame_window = 10
emotion_offsets = (20, 40)
# loading models
face_detector = Decode(facesDetect['classes_path'], facesDetect['model_path'])
emotion_classifier = load_model(emotion_model_path, compile=False)
# getting input model shapes for inference
emotion_target_size = emotion_classifier.input_shape[1:3]
emotion_window1 = []
record1 = {'angry':[0], 'disgust':[0], 'fear':[0], 'happy':[0], 'sad':[0], 'surprise':[0], 'neutral':[0]}
#record_diff = {'angry':[], 'disgust':[], 'fear':[], 'happy':[], 'sad':[], 'surprise':[], 'neutral':[]}'''
emo_record1 = []
capture = cv2.VideoCapture(0)
while True:
if True:
bgr_image = capture.read()[1]
gray_image = cv2.cvtColor(bgr_image, cv2.COLOR_BGR2GRAY)
rgb_image = cv2.cvtColor(bgr_image, cv2.COLOR_BGR2RGB)
faces = face_detector.detect_image(bgr_image)[1]
if faces is None:
faces = ()
# print(faces)
for face_coordinates in faces:
x1, y1, x2, y2 = face_coordinates
face_coordinates = [int(x1), int(y1), int(x2-x1), int(y2-y1)]
x1, x2, y1, y2 = apply_offsets(face_coordinates, emotion_offsets)
gray_face = gray_image[y1:y2, x1:x2]
try:
gray_face = cv2.resize(gray_face, (emotion_target_size))
except:
continue
gray_face = preprocess_input(gray_face, True)
gray_face = np.expand_dims(gray_face, 0)
gray_face = np.expand_dims(gray_face, -1)
emotion_prediction = emotion_classifier.predict(gray_face)
###############移動平均公式################
'''for idx, probability in enumerate(emotion_prediction[0]):
alpha = 0.5
record[emotion_labels[idx]].append(record[emotion_labels[idx]][-1] + alpha * (round(probability*100, 2)-record[emotion_labels[idx]][-1]))
emotion_prediction[0][idx] = record[emotion_labels[idx]][-1]
if len(record[emotion_labels[idx]])>10:
record[emotion_labels[idx]].pop(0)
#print(record)
#print()'''
#########################################
#################自創權重##############
emotion_prediction[0] = weights_change(emo_record1, emotion_prediction[0])
data=[]
for idx, probability in enumerate(emotion_prediction[0]):
data.append((emotion_labels[idx], probability))
rd1.append(data)
count1+=1
emo_record1.append(np.argmax(emotion_prediction))
if len(emo_record1)>10:
emo_record1.pop(0)
#######################################
emotion_probability = np.max(emotion_prediction)
emotion_label_arg = np.argmax(emotion_prediction)
emotion_text = emotion_labels[emotion_label_arg]
emotion_window1.append(emotion_text)
if len(emotion_window1) > frame_window:
emotion_window1.pop(0)
try:
emotion_mode1 = mode(emotion_window1)
except:
continue
if emotion_text == 'angry':
color = emotion_probability * np.asarray((255, 0, 0))
elif emotion_text == 'sad':
color = emotion_probability * np.asarray((0, 0, 255))
elif emotion_text == 'happy':
color = emotion_probability * np.asarray((255, 255, 0))
elif emotion_text == 'surprise':
color = emotion_probability * np.asarray((0, 255, 255))
else:
color = emotion_probability * np.asarray((0, 255, 0))
color = color.astype(int)
color = color.tolist()
draw_bounding_box(face_coordinates, rgb_image, color)
draw_text(face_coordinates, rgb_image, emotion_mode1,
color, 0, -45, 1, 1)
bgr_image = cv2.cvtColor(rgb_image, cv2.COLOR_RGB2BGR)
cv2.imshow('window_frame1', bgr_image)
if cv2.waitKey(1) & 0xFF == 27:
break
cv2.destroyAllWindows()
if not os.path.exists('images/res/'): os.mkdir('images/res/')
path_dir = os.listdir('images/test')
capture = cv2.VideoCapture(video_path)
width = int(capture.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(capture.get(cv2.CAP_PROP_FRAME_HEIGHT))
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
video_name = os.path.split(video_path)[-1]
if not os.path.exists(output_dir):
os.makedirs(output_dir)
out_path = os.path.join(output_dir, video_name)
writer = cv2.VideoWriter(out_path, fourcc, fps, (width, height))
index = 1
start = time.time()
while (1):
ret, frame = capture.read()
if not ret:
break
print('detect frame:%d' % (index))
index += 1
pimage, im_size = _decode.process_image(np.copy(frame))
image, boxes, scores, classes = _decode.detect_image(
frame, pimage, im_size, draw_image, draw_thresh)
cv2.imshow("detection", frame)
writer.write(frame)
if cv2.waitKey(110) & 0xff == 27:
break
writer.release()