def train():
dataset = voc0712.VOCDetection(root=Config.dataset_root,
transform=augmentations.SSDAugmentation(
Config.image_size, Config.MEANS))
data_loader = data.DataLoader(dataset,
Config.batch_size,
num_workers=Config.data_load_number_worker,
shuffle=True,
collate_fn=detection_collate,
pin_memory=True)
net = ssd_net_vgg.SSD()
vgg_weights = torch.load('./weights/vgg16_reducedfc.pth') #加载预训练模型
# vgg_weights = torch.load('./weights/final_20200223_VOC_100000.pth')
net = nn.DataParallel(net)
# net.apply(weights_init)
net.vgg.load_state_dict(vgg_weights)
# net.load_state_dict(vgg_weights)
# net.apply(weights_init)
if Config.use_cuda:
net = torch.nn.DataParallel(net)
net = net.cuda()
net.train()
loss_fun = loss_function.LossFun()
optimizer = optim.SGD(net.parameters(),
lr=Config.lr,
momentum=Config.momentum,
weight_decay=Config.weight_decacy)
iter = 0
step_index = 0
before_epoch = -1
for epoch in range(1000):
for step, (img, target) in enumerate(data_loader):
if Config.use_cuda:
img = img.cuda()
target = [ann.cuda() for ann in target]
img = torch.Tensor(img)
loc_pre, conf_pre = net(img)
priors = utils.default_prior_box()
optimizer.zero_grad()
loss_l, loss_c = loss_fun((loc_pre, conf_pre), target, priors)
loss = loss_l + loss_c
loss.backward()
optimizer.step()
if iter % 1 == 0 or before_epoch != epoch:
print('epoch : ', epoch, ' iter : ', iter, ' step : ', step,
' loss : ', loss.item())
before_epoch = epoch
iter += 1
if iter in Config.lr_steps:
step_index += 1
adjust_learning_rate(optimizer, Config.gamma, step_index)
if iter % 10000 == 0 and iter != 0: #每1万次训练保存一个模型
torch.save(
net.state_dict(), 'weights/final_20200226_VOC_' +
repr(100000 + iter) + '.pth')
if iter >= Config.max_iter:
break
torch.save(net.state_dict(), 'weights/final_20200223_voc_200000.pth')
def test_one_picture(picture_path):
if torch.cuda.is_available():
torch.set_default_tensor_type('torch.cuda.FloatTensor')
colors_tableau = [(255, 255, 255), (31, 119, 180), (174, 199, 232),
(255, 127, 14), (255, 187, 120), (44, 160, 44),
(152, 223, 138), (214, 39, 40), (255, 152, 150),
(148, 103, 189), (197, 176, 213), (140, 86, 75),
(196, 156, 148), (227, 119, 194), (247, 182, 210),
(127, 127, 127), (199, 199, 199), (188, 189, 34),
(219, 219, 141), (23, 190, 207), (158, 218, 229),
(158, 218, 229), (158, 218, 229)]
net = SSD() # initialize SSD
net = torch.nn.DataParallel(net)
net.train(mode=False)
net.load_state_dict(
torch.load('./weights/ssd_voc_100EPOCH.pth',
map_location=lambda storage, loc: storage))
image = cv2.imread(picture_path, cv2.IMREAD_COLOR)
x = cv2.resize(image, (300, 300)).astype(np.float32)
x -= (104.0, 117.0, 123.0)
x = x.astype(np.float32)
x = x[:, :, ::-1].copy()
# plt.imshow(x)
x = torch.from_numpy(x).permute(2, 0, 1)
xx = Variable(x.unsqueeze(0)) # wrap tensor in Variable
if torch.cuda.is_available():
xx = xx.cuda()
y = net(xx)
softmax = nn.Softmax(dim=-1)
detect = Detect(config.class_num, 0, 200, 0.01, 0.45)
priors = utils.default_prior_box()
loc, conf = y
loc = torch.cat([o.view(o.size(0), -1) for o in loc], 1)
conf = torch.cat([o.view(o.size(0), -1) for o in conf], 1)
detections = detect(loc.view(loc.size(0), -1, 4),
softmax(conf.view(conf.size(0), -1, config.class_num)),
torch.cat([o.view(-1, 4) for o in priors], 0)).data
labels = VOC_CLASSES
# scale each detection back up to the image
scale = torch.Tensor(image.shape[1::-1]).repeat(2)
for i in range(detections.size(1)):
for j in range(detections.size(2)):
if detections[0, i, j, 0] >= 0.1:
score = detections[0, i, j, 0]
label_name = labels[i - 1]
display_txt = '%s: %.2f' % (label_name, score)
pt = (detections[0, i, j, 1:] * scale).cpu().numpy()
color = colors_tableau[i]
cv2.rectangle(image, (pt[0], pt[1]), (pt[2], pt[3]), color, 2)
cv2.putText(image, display_txt, (int(pt[0]), int(pt[1]) + 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.4, (255, 255, 255), 1,
8)
cv2.imshow('test', image)
cv2.waitKey(100000)
def Detect(self, image):
img_id = 60
# image = cv2.imread('./pic/00000.png', cv2.IMREAD_COLOR)
x = cv2.resize(image, (300, 300)).astype(np.float32)
x -= (104.0, 117.0, 123.0)
x = x.astype(np.float32)
x = x[:, :, ::-1].copy()
# plt.imshow(x)
x = torch.from_numpy(x).permute(2, 0, 1)
xx = Variable(x.unsqueeze(0)) # wrap tensor in Variable
if torch.cuda.is_available():
xx = xx.cuda()
y = self.net(xx)
softmax = nn.Softmax(dim=-1)
detect = Detect(config.class_num, 0, 200, 0.01, 0.45)
priors = utils.default_prior_box()
loc, conf = y
loc = torch.cat([o.view(o.size(0), -1) for o in loc], 1)
conf = torch.cat([o.view(o.size(0), -1) for o in conf], 1)
detections = detect(
loc.view(loc.size(0), -1, 4),
softmax(conf.view(conf.size(0), -1, config.class_num)),
torch.cat([o.view(-1, 4) for o in priors], 0)).data
labels = VOC_CLASSES
top_k = 10
# plt.imshow(rgb_image) # plot the image for matplotlib
# scale each detection back up to the image
result_all = []
scale = torch.Tensor(image.shape[1::-1]).repeat(2)
for i in range(detections.size(1)):
j = 0
while detections[0, i, j, 0] >= 0.4:
result_single = []
score = detections[0, i, j, 0]
label_name = labels[i - 1]
pt = (detections[0, i, j, 1:] * scale).cpu().numpy()
j += 1
result_single.append(label_name)
result_single.append(score)
result_single.append(pt[0])
result_single.append(pt[1])
result_single.append(pt[2])
result_single.append(pt[3])
result_all.append(result_single)
#display_txt = '%s: %.2f'%(label_name, score)
#coords = (pt[0], pt[1]), pt[2]-pt[0]+1, pt[3]-pt[1]+1
#color = colors_tableau[i]
#cv2.rectangle(image,(pt[0],pt[1]), (pt[2],pt[3]), color, 2)
#cv2.putText(image, display_txt, (int(pt[0]), int(pt[1]) + 10), cv2.FONT_HERSHEY_SIMPLEX, 0.4, (255,255,255), 1, 8)
return result_all
img_id = 60
name = 'dnf_test'
image = cv2.imread('./' + name + '.jpg', cv2.IMREAD_COLOR)
x = cv2.resize(image, (300, 300)).astype(np.float32)
x -= (104.0, 117.0, 123.0)
x = x.astype(np.float32)
x = x[:, :, ::-1].copy()
# plt.imshow(x)
x = torch.from_numpy(x).permute(2, 0, 1)
xx = Variable(x.unsqueeze(0)) # wrap tensor in Variable
if torch.cuda.is_available():
xx = xx.cuda()
y = net(xx)
softmax = nn.Softmax(dim=-1)
detect = Detect(config.class_num, 0, 200, 0.01, 0.45)
priors = utils.default_prior_box()
loc, conf = y
loc = torch.cat([o.view(o.size(0), -1) for o in loc], 1)
conf = torch.cat([o.view(o.size(0), -1) for o in conf], 1)
detections = detect(loc.view(loc.size(0), -1, 4),
softmax(conf.view(conf.size(0), -1, config.class_num)),
torch.cat([o.view(-1, 4) for o in priors], 0)).data
labels = VOC_CLASSES
top_k = 10
# plt.imshow(rgb_image) # plot the image for matplotlib
# scale each detection back up to the image
def show_img(self):
global temp_t
success, self.img = self.camera.read()
if success:
self.Image_num += 1
if self.Image_num % 10 == 9:
frame_rate = 10 / (time.clock() - self.timelb)
self.FmRateLCD.display(frame_rate)
self.timelb = time.clock()
if self.case == 0:
showImg = cv2.cvtColor(self.img, cv2.COLOR_BGR2RGB)
showImg = qimage2ndarray.array2qimage(showImg)
self.Camera_2.setPixmap(QPixmap(showImg)) # 展示图片
self.Camera_2.show()
if self.case == 1:
bounding_boxes, landmarks = detect_faces(self.img)
self.img = show_bboxes(self.img, bounding_boxes, landmarks)
showImg = cv2.cvtColor(self.img, cv2.COLOR_BGR2RGB)
showImg = qimage2ndarray.array2qimage(showImg)
self.Camera_2.setPixmap(QPixmap(showImg)) # 展示图片
self.Camera_2.show()
if self.case == 2:
img_copy = self.img.copy()
frag_gray = False
self.time_ing = time.time()
# point=[100,0,540,480]
if self.frag_cap:
bounding_boxes, landmarks = detect_faces(self.img)
print('正在定位······')
if len(bounding_boxes) == 1:
self.point.clear()
for b in bounding_boxes:
b = [int(round(value)) for value in b]
for i in b:
self.point.append(i)
self.frag_cap = False
# print(point)
# cv2.rectangle(draw, (b[0], b[1]), (b[2], b[3]), (0, 255, 0), 2)
# 裁剪坐标为[y0:y1, x0:x1]
if not self.frag_cap:
if self.point[0] < 540:
self.img = self.img[self.point[1] - 10:479,
self.point[0] - 100:self.point[2] +
100]
else:
self.img = self.img[self.point[1] - 10:479,
self.point[0] - 100:639]
else:
self.img = self.img[1:479, 1:640]
if int(self.time_ing - self.time_first) % 60 == 0:
self.frag_cap = True
else:
self.frag_cap = False
bounding_boxes, landmarks = detect_faces(self.img)
#通过MTCNN人脸框判断，当检测不到人脸时判断低头or瞌睡
if len(bounding_boxes) == 0:
self.nod_fps += 1
if self.nod_fps >= 3:
self.Head_state.setText('点头')
self.nod_count += 1
if len(bounding_boxes) > 0:
self.nod_fps = 0
#通过头部姿态欧拉角角度变化判断是否摇头
if len(bounding_boxes) > 0:
Head_Y_X_Z = get_head_pose(landmarks)
print('pitch:{}, yaw:{}, roll:{}'.format(
Head_Y_X_Z[1], Head_Y_X_Z[2], Head_Y_X_Z[3]))
if (Head_Y_X_Z[2] < -0.75):
self.shake_fps_l += 1
if (Head_Y_X_Z[2] >= -0.75):
self.shake_fps_l = 0
if self.shake_fps_l >= 5:
self.shake_count += 1
self.Head_state.setText('摇头')
if Head_Y_X_Z[3] >= 0.30:
self.shake_fps_r += 1
if self.shake_fps_r >= 5:
self.shake_count += 1
self.Head_state.setText('摇头')
if Head_Y_X_Z[3] < 0.30:
self.shake_fps_r = 0
# print(Head_Y_X_Z[1])
# print(Head_Y_X_Z[2])
# print(Head_Y_X_Z[3])
if time.time() - self.nod_start > 3:
self.Head_state.setText('')
if time.time() - self.shake_start > 3:
self.Head_state.setText('')
# 计算低头频率 每10s计算一次
if time.time() - self.nod_start > 10:
times = time.time() - self.nod_start
self.nod_freq = self.nod_count / times
self.nod_start = time.time()
self.Nod_LCD.display(self.nod_freq)
# 计算摇头频率
if time.time() - self.shake_start > 10:
times = time.time() - self.shake_start
self.shake_freq = self.shake_count / times
self.shake_start = time.time()
self.shake_LCD.display(self.shake_freq)
if len(bounding_boxes) > 0:
Emotions = get_emotion(
get_face_expression(self.img, bounding_boxes))
self.Emotion.setText(Emotions[1])
self.Emotion_pred.display(float(Emotions[0]))
# print(Emotions)
canvas = cv2.imread('img_resource/label_pred.jpg',
flags=cv2.IMREAD_UNCHANGED)
for (i,
(emotion,
prob)) in enumerate(zip(self.EMOTIONS, Emotions[2])):
# text = "{}: {:.2f}%".format(emotion, prob * 100)
text = "{:.2f}%".format(prob * 100)
# 绘制表情类和对应概率的条形图
w = int(prob * 180)
# print(text)
# canvas = 255 * np.ones((250, 300, 3), dtype="uint8")
cv2.rectangle(canvas, (0, (i * 44) + 25),
(w, (i * 43) + 40), (100, 200, 130), -1)
cv2.putText(canvas, text, (170, (i * 43) + 40),
cv2.FONT_HERSHEY_DUPLEX, 0.6, (0, 0, 0), 1)
show = cv2.cvtColor(canvas, cv2.COLOR_BGR2RGB)
showImage = QtGui.QImage(show.data, show.shape[1],
show.shape[0],
QtGui.QImage.Format_RGB888)
# cv2.imshow('test', showImage)
# showImg=QPixmap(showImage)
self.label_pred_img.setPixmap(
QtGui.QPixmap.fromImage(showImage))
# # print('test')
# print('Head_Y_X_Z')
# print(Head_Y_X_Z)
x = cv2.resize(self.img, (300, 300)).astype(np.float32)
flag_B = True # 是否闭眼的flag
flag_Y = False
num_rec = 0 # 检测到的眼睛的数量
# 分界线
x -= self.img_mean
x = x.astype(np.float32)
x = x[:, :, ::-1].copy()
x = torch.from_numpy(x).permute(2, 0, 1)
xx = Variable(x.unsqueeze(0))
# if torch.cuda.is_available():
# xx = xx.cuda()
xx = xx.cuda()
y = self.net(xx)
softmax = nn.Softmax(dim=-1)
detect = Detect(config.class_num, 0, 200, 0.01, 0.45)
priors = utils.default_prior_box()
loc, conf = y
loc = torch.cat([o.view(o.size(0), -1) for o in loc], 1)
conf = torch.cat([o.view(o.size(0), -1) for o in conf], 1)
detections = detect(
loc.view(loc.size(0), -1, 4),
softmax(conf.view(conf.size(0), -1, config.class_num)),
torch.cat([o.view(-1, 4) for o in priors], 0)).data
labels = VOC_CLASSES
# 将检测结果放置于图片上
scale = torch.Tensor(self.img.shape[1::-1]).repeat(2)
self.img = show_bboxes(self.img, bounding_boxes, landmarks)
for i in range(detections.size(1)):
j = 0
while detections[0, i, j, 0] >= 0.4:
score = detections[0, i, j, 0]
label_name = labels[i - 1]
if label_name == 'calling' and score > 0.8:
self.Danger_state.setText('打电话')
self.danger_count += 1
frag_gray = True
if label_name == 'smoke' and score > 0.8:
self.Danger_state.setText('吸烟')
self.danger_count += 1
frag_gray = True
if label_name != 'smoke' and label_name != 'calling':
self.danger_t += 1
if self.danger_t >= 20:
self.Danger_state.setText('')
self.danger_t = 0
if label_name == 'open_eye':
self.open_t += 1
if self.open_t >= 20:
self.Eyes_state.setText('')
self.open_t = 0
if label_name == 'closed_mouth':
self.Mouth_state.setText(' ')
if label_name == 'closed_eye':
flag_B = False
frag_gray = True
if label_name == 'open_mouth':
flag_Y = True
display_txt = '%s:%.2f' % (label_name, score)
pt = (detections[0, i, j, 1:] * scale).cpu().numpy()
self.coords = (
pt[0], pt[1]), pt[2] - pt[0] + 1, pt[3] - pt[1] + 1
color = self.colors_tableau[i]
cv2.rectangle(self.img, (pt[0], pt[1]), (pt[2], pt[3]),
color, 2)
cv2.putText(self.img, display_txt,
(int(pt[0]), int(pt[1]) + 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.4,
(255, 255, 255), 1, 8)
j += 1
num_rec += 1
# cv2.imshow('test', self.img)
if num_rec > 0:
if flag_B:
# print(' 1:eye-open')
self.list_B = np.append(self.list_B, 1) # 睁眼为‘1’
self.list_blink = np.append(self.list_blink, 1)
else:
# print(' 0:eye-closed')
self.list_B = np.append(self.list_B, 0) # 闭眼为‘0’
self.list_blink = np.append(self.list_blink, 0)
self.list_blink = np.delete(self.list_blink, 0)
self.list_B = np.delete(self.list_B, 0)
if flag_Y:
self.list_Y = np.append(self.list_Y, 1)
else:
self.list_Y = np.append(self.list_Y, 0)
self.list_Y = np.delete(self.list_Y, 0)
else:
self.Msg.clear()
self.Msg.setPlainText('Nothing detected.')
# print(list)
# 实时计算PERCLOS
self.perclos = 1 - np.average(self.list_blink)
# print('perclos={:f}'.format(perclos))
self.PERCLOS.display(self.perclos)
if self.list_B[8] == 1 and self.list_B[9] == 0:
# 如果上一帧为’1‘，此帧为’0‘则判定为眨眼
self.Eyes_state.setText('眨眼')
self.blink_count += 1
frag_gray = True
str = datetime.datetime.now().strftime("%H:%M:%S")
self.State_record.append(str + '：眨眼')
# img_copy=cv2.cvtColor(img_copy,cv2.COLOR_RGB2GRAY)
blink_T = time.time() - self.blink_start
if blink_T > 30:
# 每30秒计算一次眨眼频率
blink_freq = self.blink_count / blink_T
self.blink_start = time.time()
self.blink_count = 0
print('blink_freq={:f}'.format(blink_freq))
self.Blink_freq.display(blink_freq * 2)
# 检测打哈欠
# if Yawn(list_Y,list_Y1):
if (self.list_Y[len(self.list_Y) -
len(self.list_Y1):] == self.list_Y1).all():
# print('----------------------打哈欠----------------------')
self.Mouth_state.setText('打哈欠')
self.yawn_count += 1
frag_gray = True
str = datetime.datetime.now().strftime("%H:%M:%S")
self.State_record.append(str + '：打哈欠')
self.list_Y = np.zeros(50)
# 计算打哈欠频率
yawn_T = time.time() - self.yawn_start
if yawn_T > 60:
yawn_freq = self.yawn_count / yawn_T
self.yawn_start = time.time()
self.yawn_count = 0
print('yawn_freq={:f}'.format(yawn_freq))
self.Yawn_freq.display(yawn_freq)
# 计算危险行为频率
DangerAct_T = time.time() - self.danger_start
if DangerAct_T > 60:
danger_freq = self.danger_count / DangerAct_T
self.danger_start = time.time()
self.danger_count = 0
print('danger_freq={:f}'.format(danger_freq))
self.Danger_LCD.display(danger_freq)
if (self.perclos > 0.4):
# print('疲劳')
self.State.setText('疲劳')
elif (self.blink_freq > 0.3):
# print('疲劳')
self.State.setText('疲劳')
self.blink_freq = 0 # 如果因为眨眼频率判断疲劳，则初始化眨眼频率
elif (self.yawn_freq > 5.0 / 60):
# print("疲劳")
self.State.setText('疲劳')
self.yawn_freq = 0 # 初始化，同上
else:
self.State.setText('清醒')
if not frag_gray:
showImg = cv2.cvtColor(img_copy, cv2.COLOR_BGR2RGB)
else:
if self.isRecordImg:
str = datetime.datetime.now().strftime(
"%Y_%m_%d_%H_%M_%S")
temp = 'ImgRecord/' + str + '.jpg'
cv2.imwrite(temp, img_copy)
showImg = cv2.cvtColor(img_copy, cv2.COLOR_RGB2GRAY)
showImg = qimage2ndarray.array2qimage(showImg)
self.Camera_2.setPixmap(QPixmap(showImg)) # 展示图片
self.Camera_2.show()
if self.case == 3:
img_copy = self.img.copy()
frag_gray = False
self.time_ing = time.time()
# point=[100,0,540,480]
if self.frag_cap:
bounding_boxes, landmarks = detect_faces(self.img)
print('正在定位······')
if len(bounding_boxes) == 1:
self.point.clear()
for b in bounding_boxes:
b = [int(round(value)) for value in b]
for i in b:
self.point.append(i)
self.frag_cap = False
# print(point)
# cv2.rectangle(draw, (b[0], b[1]), (b[2], b[3]), (0, 255, 0), 2)
# 裁剪坐标为[y0:y1, x0:x1]
if not self.frag_cap:
if self.point[0] < 540:
self.img = self.img[self.point[1] - 10:479,
self.point[0] - 100:self.point[2] +
100]
else:
self.img = self.img[self.point[1] - 10:479,
self.point[0] - 100:639]
else:
self.img = self.img[1:479, 1:640]
if int(self.time_ing - self.time_first) % 60 == 0:
self.frag_cap = True
else:
self.frag_cap = False
bounding_boxes, landmarks = detect_faces(self.img)
# 通过MTCNN人脸框判断，当检测不到人脸时判断低头or瞌睡
if len(bounding_boxes) == 0:
self.nod_fps += 1
if self.nod_fps >= 3:
self.Head_state.setText('点头')
self.nod_count += 1
if len(bounding_boxes) > 0:
self.nod_fps = 0
# 通过头部姿态欧拉角角度变化判断是否摇头
if len(bounding_boxes) > 0:
Head_Y_X_Z = get_head_pose(landmarks)
print('pitch:{}, yaw:{}, roll:{}'.format(
Head_Y_X_Z[1], Head_Y_X_Z[2], Head_Y_X_Z[3]))
if (Head_Y_X_Z[2] < -0.75):
self.shake_fps_l += 1
if (Head_Y_X_Z[2] >= -0.75):
self.shake_fps_l = 0
if self.shake_fps_l >= 5:
self.shake_count += 1
self.Head_state.setText('摇头')
if Head_Y_X_Z[3] >= 0.30:
self.shake_fps_r += 1
if self.shake_fps_r >= 5:
self.shake_count += 1
self.Head_state.setText('摇头')
if Head_Y_X_Z[3] < 0.30:
self.shake_fps_r = 0
# print(Head_Y_X_Z[1])
# print(Head_Y_X_Z[2])
# print(Head_Y_X_Z[3])
if time.time() - self.nod_start > 3:
self.Head_state.setText('')
if time.time() - self.shake_start > 3:
self.Head_state.setText('')
# 计算低头频率 每10s计算一次
if time.time() - self.nod_start > 10:
times = time.time() - self.nod_start
self.nod_freq = self.nod_count / times
self.nod_start = time.time()
self.Nod_LCD.display(self.nod_freq)
# 计算摇头频率
if time.time() - self.shake_start > 10:
times = time.time() - self.shake_start
self.shake_freq = self.shake_count / times
self.shake_start = time.time()
self.shake_LCD.display(self.shake_freq)
if len(bounding_boxes) > 0:
Emotions = get_emotion(
get_face_expression(self.img, bounding_boxes))
self.Emotion.setText(Emotions[1])
self.Emotion_pred.display(float(Emotions[0]))
# print(Emotions)
canvas = cv2.imread('img_resource/label_pred.jpg',
flags=cv2.IMREAD_UNCHANGED)
for (i,
(emotion,
prob)) in enumerate(zip(self.EMOTIONS, Emotions[2])):
# text = "{}: {:.2f}%".format(emotion, prob * 100)
text = "{:.2f}%".format(prob * 100)
# 绘制表情类和对应概率的条形图
w = int(prob * 180)
# print(text)
# canvas = 255 * np.ones((250, 300, 3), dtype="uint8")
cv2.rectangle(canvas, (0, (i * 44) + 25),
(w, (i * 43) + 40), (100, 200, 130), -1)
cv2.putText(canvas, text, (170, (i * 43) + 40),
cv2.FONT_HERSHEY_DUPLEX, 0.6, (0, 0, 0), 1)
show = cv2.cvtColor(canvas, cv2.COLOR_BGR2RGB)
showImage = QtGui.QImage(show.data, show.shape[1],
show.shape[0],
QtGui.QImage.Format_RGB888)
# cv2.imshow('test', showImage)
# showImg=QPixmap(showImage)
self.label_pred_img.setPixmap(
QtGui.QPixmap.fromImage(showImage))
# # print('test')
# print('Head_Y_X_Z')
# print(Head_Y_X_Z)
x = cv2.resize(self.img, (300, 300)).astype(np.float32)
flag_B = True # 是否闭眼的flag
flag_Y = False
num_rec = 0 # 检测到的眼睛的数量
# 分界线
x -= self.img_mean
x = x.astype(np.float32)
x = x[:, :, ::-1].copy()
x = torch.from_numpy(x).permute(2, 0, 1)
xx = Variable(x.unsqueeze(0))
# if torch.cuda.is_available():
# xx = xx.cuda()
xx = xx.cuda()
y = self.net(xx)
softmax = nn.Softmax(dim=-1)
detect = Detect(config.class_num, 0, 200, 0.01, 0.45)
priors = utils.default_prior_box()
loc, conf = y
loc = torch.cat([o.view(o.size(0), -1) for o in loc], 1)
conf = torch.cat([o.view(o.size(0), -1) for o in conf], 1)
detections = detect(
loc.view(loc.size(0), -1, 4),
softmax(conf.view(conf.size(0), -1, config.class_num)),
torch.cat([o.view(-1, 4) for o in priors], 0)).data
labels = VOC_CLASSES
# 将检测结果放置于图片上
scale = torch.Tensor(self.img.shape[1::-1]).repeat(2)
self.img = show_bboxes(self.img, bounding_boxes, landmarks)
for i in range(detections.size(1)):
j = 0
while detections[0, i, j, 0] >= 0.4:
score = detections[0, i, j, 0]
label_name = labels[i - 1]
if label_name == 'calling' and score > 0.8:
self.Danger_state.setText('打电话')
self.danger_count += 1
frag_gray = True
if label_name == 'smoke' and score > 0.8:
self.Danger_state.setText('吸烟')
self.danger_count += 1
frag_gray = True
if label_name != 'smoke' and label_name != 'calling':
self.danger_t += 1
if self.danger_t >= 20:
self.Danger_state.setText('')
self.danger_t = 0
if label_name == 'open_eye':
self.open_t += 1
if self.open_t >= 20:
self.Eyes_state.setText('')
self.open_t = 0
if label_name == 'closed_mouth':
self.Mouth_state.setText(' ')
if label_name == 'closed_eye':
flag_B = False
frag_gray = True
if label_name == 'open_mouth':
flag_Y = True
display_txt = '%s:%.2f' % (label_name, score)
pt = (detections[0, i, j, 1:] * scale).cpu().numpy()
self.coords = (
pt[0], pt[1]), pt[2] - pt[0] + 1, pt[3] - pt[1] + 1
color = self.colors_tableau[i]
cv2.rectangle(self.img, (pt[0], pt[1]), (pt[2], pt[3]),
color, 2)
cv2.putText(self.img, display_txt,
(int(pt[0]), int(pt[1]) + 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.4,
(255, 255, 255), 1, 8)
j += 1
num_rec += 1
# cv2.imshow('test', self.img)
if num_rec > 0:
if flag_B:
# print(' 1:eye-open')
self.list_B = np.append(self.list_B, 1) # 睁眼为‘1’
self.list_blink = np.append(self.list_blink, 1)
else:
# print(' 0:eye-closed')
self.list_B = np.append(self.list_B, 0) # 闭眼为‘0’
self.list_blink = np.append(self.list_blink, 0)
self.list_blink = np.delete(self.list_blink, 0)
self.list_B = np.delete(self.list_B, 0)
if flag_Y:
self.list_Y = np.append(self.list_Y, 1)
else:
self.list_Y = np.append(self.list_Y, 0)
self.list_Y = np.delete(self.list_Y, 0)
else:
self.Msg.clear()
self.Msg.setPlainText('Nothing detected.')
# print(list)
# 实时计算PERCLOS
self.perclos = 1 - np.average(self.list_blink)
# print('perclos={:f}'.format(perclos))
self.PERCLOS.display(self.perclos)
if self.list_B[8] == 1 and self.list_B[9] == 0:
# 如果上一帧为’1‘，此帧为’0‘则判定为眨眼
self.Eyes_state.setText('眨眼')
self.blink_count += 1
frag_gray = True
str = datetime.datetime.now().strftime("%H:%M:%S")
self.State_record.append(str + '：眨眼')
# img_copy=cv2.cvtColor(img_copy,cv2.COLOR_RGB2GRAY)
blink_T = time.time() - self.blink_start
if blink_T > 30:
# 每30秒计算一次眨眼频率
blink_freq = self.blink_count / blink_T
self.blink_start = time.time()
self.blink_count = 0
print('blink_freq={:f}'.format(blink_freq))
self.Blink_freq.display(blink_freq * 2)
# 检测打哈欠
# if Yawn(list_Y,list_Y1):
if (self.list_Y[len(self.list_Y) -
len(self.list_Y1):] == self.list_Y1).all():
# print('----------------------打哈欠----------------------')
self.Mouth_state.setText('打哈欠')
self.yawn_count += 1
frag_gray = True
str = datetime.datetime.now().strftime("%H:%M:%S")
self.State_record.append(str + '：打哈欠')
self.list_Y = np.zeros(50)
# 计算打哈欠频率
yawn_T = time.time() - self.yawn_start
if yawn_T > 60:
yawn_freq = self.yawn_count / yawn_T
self.yawn_start = time.time()
self.yawn_count = 0
print('yawn_freq={:f}'.format(yawn_freq))
self.Yawn_freq.display(yawn_freq)
# 计算危险行为频率
DangerAct_T = time.time() - self.danger_start
if DangerAct_T > 60:
danger_freq = self.danger_count / DangerAct_T
self.danger_start = time.time()
self.danger_count = 0
print('danger_freq={:f}'.format(danger_freq))
self.Danger_LCD.display(danger_freq)
if (self.perclos > 0.4):
# print('疲劳')
self.State.setText('疲劳')
elif (self.blink_freq > 0.3):
# print('疲劳')
self.State.setText('疲劳')
self.blink_freq = 0 # 如果因为眨眼频率判断疲劳，则初始化眨眼频率
elif (self.yawn_freq > 5.0 / 60):
# print("疲劳")
self.State.setText('疲劳')
self.yawn_freq = 0 # 初始化，同上
else:
self.State.setText('清醒')
if not frag_gray:
showImg = cv2.cvtColor(img_copy, cv2.COLOR_BGR2RGB)
else:
if self.isRecordImg:
str = datetime.datetime.now().strftime(
"%Y_%m_%d_%H_%M_%S")
temp = 'ImgRecord/' + str + '.jpg'
cv2.imwrite(temp, img_copy)
showImg = cv2.cvtColor(img_copy, cv2.COLOR_RGB2GRAY)
self.State_record.moveCursor(QTextCursor.End)
showImg = qimage2ndarray.array2qimage(showImg)
self.Camera_2.setPixmap(QPixmap(showImg)) # 展示图片
self.Camera_2.show()
def train():
# , ("core_500","coreless_5000")
dataset = ml_data.SIXrayDetection(
Config.dataset_root, ['core_500', 'coreless_5000'],
augmentations.SSDAugmentation(Config.image_size, Config.MEANS))
data_loader = data.DataLoader(dataset,
Config.batch_size,
num_workers=Config.data_load_number_worker,
shuffle=True,
collate_fn=detection_collate,
pin_memory=True)
net = ssd_net_vgg.SSD()
# vgg_weights = torch.load('./weights/vgg16_reducedfc.pth')
vgg_weights = torch.load('./weights/vgg16_reducedfc.pth')
net.apply(weights_init)
net.vgg.load_state_dict(vgg_weights)
# net.apply(weights_init)
if Config.use_cuda:
net = torch.nn.DataParallel(net)
net = net.cuda()
net.train()
loss_fun = loss_function.LossFun()
optimizer = optim.SGD(net.parameters(),
lr=Config.lr,
momentum=Config.momentum,
weight_decay=Config.weight_decacy)
iter = 0
step_index = 0
before_epoch = -1
for epoch in range(Config.epoch_num):
for step, (img, target) in enumerate(data_loader):
if Config.use_cuda:
img = img.cuda()
target = [ann.cuda() for ann in target]
try:
img = torch.Tensor(img)
except TypeError as e:
print(e)
loc_pre, conf_pre = net(img)
priors = utils.default_prior_box()
optimizer.zero_grad()
loss_l, loss_c = loss_fun((loc_pre, conf_pre), target, priors)
loss = loss_l + loss_c
loss.backward()
optimizer.step()
if iter % 1 == 0 or before_epoch != epoch:
print('epoch : ', epoch, ' iter : ', iter, ' step : ', step,
' loss : ', loss.item())
before_epoch = epoch
iter += 1
if iter in Config.lr_steps:
step_index += 1
adjust_learning_rate(optimizer, Config.gamma, step_index)
if iter % 10000 == 0 and iter != 0:
torch.save(net.state_dict(),
'weights/ssd300_VOC_' + repr(iter) + '.pth')
if iter >= Config.max_iter:
break
torch.save(net.state_dict(), 'weights/core500.pth')
def test_net(save_folder,
net,
cuda,
dataset,
transform,
top_k,
im_size=300,
thresh=0.05):
det_result_core_file = 'predicted_file/det_test_带电芯充电宝3.txt'
det_result_core_less_file = 'predicted_file/det_test_不带电芯充电宝3.txt'
num_images = len(dataset)
# all_boxes = [[[] for _ in range(num_images)]
# for _ in range(len(labelmap) + 1)]
# output_dir = get_output_dir(args.SIXray_root, set_type)
# det_file = os.path.join(output_dir, 'detections.pkl')
for root, dirs, files in os.walk(dataset):
# root 表示当前正在访问的文件夹路径
# dirs 表示该文件夹下的子目录名list
# files 表示该文件夹下的文件list
# 遍历文件
for file in files:
file_with_path = os.path.join(root, file)
#print('Testing image {:d}/{:d}....'.format(id+1, num_images))
#a = dataset.pull_item(id)
#im, gt, h, w, im_og, img_id= dataset.pull_item(id)
# 这里im的颜色偏暗，因为BaseTransform减去了一个mean
# im_saver = cv2.resize(im[(a2,a1,0),:,:].permute((a1,a2,0)).numpy(), (w,h))
im_og = cv2.imread(file_with_path, cv2.IMREAD_COLOR)
x = cv2.resize(im_og, (300, 300)).astype(np.float32)
x -= (104.0, 117.0, 123.0)
x = x.astype(np.float32)
x = x[:, :, ::-1].copy()
# plt.imshow(x)
x = torch.from_numpy(x).permute(2, 0, 1)
xx = Variable(x.unsqueeze(0))
if args.cuda:
xx = x.cuda()
y = net(xx)
softmax = nn.Softmax(dim=-1)
detect = Detect(config.class_num, 0, 200, 0.01, 0.45)
priors = utils.default_prior_box()
loc, conf = y
loc = torch.cat([o.view(o.size(0), -1) for o in loc], 1)
conf = torch.cat([o.view(o.size(0), -1) for o in conf], 1)
detections = detect(
loc.view(loc.size(0), -1, 4),
softmax(conf.view(conf.size(0), -1, config.class_num)),
torch.cat([o.view(-1, 4) for o in priors], 0)).data
labels = ['core', 'coreless']
# plt.imshow(rgb_image) # plot the image for matplotlib
# scale each detection back up to the image
scale = torch.Tensor(im_og.shape[1::-1]).repeat(2)
for i in range(detections.size(1)):
for j in range(detections.size(2)):
if detections[0, i, j, 0] >= 0.01:
score = detections[0, i, j, 0]
label_name = labels[i - 1]
display_txt = '%s: %.2f' % (label_name, score)
pt = (detections[0, i, j, 1:] * scale).cpu().numpy()
coords = (pt[0],
pt[1]), pt[2] - pt[0] + 1, pt[3] - pt[1] + 1
color = (0, 0, 255)
cv2.rectangle(im_og, (pt[0], pt[1]), (pt[2], pt[3]),
color, 2)
cv2.putText(im_og, display_txt,
(int(pt[0]), int(pt[1]) + 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.4, (255, 0, 0),
1, 8)
text = '%s %.2f %.2f %.2f %.2f %.2f' % (
file[:-4], score, pt[0], pt[1], pt[2], pt[3])
if label_name == 'core':
with open(det_result_core_file, 'a+') as f:
f.write(text + '\n')
if label_name == 'coreless':
with open(det_result_core_less_file, 'a+') as f:
f.write(text + '\n')
