def detcet(self, img, threshold):
"""归一化"""
copy_img = (img.copy() - 127.5) / 127.5
origin_h, origin_w, _ = copy_img.shape
print(origin_h, origin_w)
"""
计算原始输入图像
每次缩放比例
"""
scales = utils.caculateScales(img)
print(scales)
out = []
"""
粗略计算人脸框
Pnet部分
"""
for scale in scales:
hs = int(origin_h * scale)
ws = int(origin_w * scale)
scale_img = cv2.resize(copy_img, (ws, hs))
#print(ws, hs)
inputs = scale_img.reshape(1, *scale_img.shape)
output = self.Pnet.predict(inputs)
out.append(output)
image_num = len(scales)
rectangles = []
for i in range(image_num):
"""有人脸的概率"""
cls_prob = out[i][0][0][:, :, 1]
"""有人脸的框对应的位置"""
roi = out[i][1][0]
"""取出每个缩放后图片的长宽"""
out_h, out_w = cls_prob.shape
out_side = max(out_h, out_w)
#print(cls_prob.shape)
"""解码过程"""
rectangel = utils.detect_face_12net(cls_prob, roi, out_side,
1 / scales[i], origin_w,
origin_h, threshold[0])
rectangles.extend(rectangel)
print(np.shape(rectangles))
# for i in range(len(rectangles)):
# bbox = rectangles[i]
# crop_img = img[int(bbox[1]):int(bbox[3]), int(bbox[0]):int(bbox[2])]
# if bbox[3] >= 80:
# cv2.imshow('crop_img', crop_img)
# cv2.waitKey(0)
"""进行非极大抑制"""
rectangles = utils.NMS(rectangles, 0.7)
if len(rectangles) == 0:
return rectangles
"""
稍微精确计算人脸框
Rnet部分
"""
predict_24_batch = []
for rectangel in rectangles:
crop_img = copy_img[int(rectangel[1]):int(rectangel[3]),
int(rectangel[0]):int(rectangel[2])]
scale_img = cv2.resize(crop_img, (24, 24))
predict_24_batch.append(scale_img)
predict_24_batch = np.array(predict_24_batch)
out = self.Rnet.predict(predict_24_batch)
"""可信度"""
cls_prob = out[0]
cls_prob = np.array(cls_prob)
"""如何调整某一张图片的rectangel"""
roi_prob = out[1]
roi_prob = np.array(roi_prob)
rectangles = utils.filter_face_24net(cls_prob, roi_prob, rectangles,
origin_w, origin_h, threshold[1])
print(np.shape(rectangles))
if len(rectangles) == 0:
return rectangles
"""
计算人脸框
Onet部分
"""
predict_batch = []
for rectangel in rectangles:
crop_img = copy_img[int(rectangel[1]):int(rectangel[3]),
int(rectangel[0]):int(rectangel[2])]
scale_img = cv2.resize(crop_img, (48, 48))
predict_batch.append(scale_img)
predict_batch = np.array(predict_batch)
out = self.Onet.predict(predict_batch)
cls_prob = out[0]
roi_prob = out[1]
pts_prob = out[2]
rectangles = utils.filter_face_48net(cls_prob, roi_prob, pts_prob,
rectangles, origin_w, origin_h,
threshold[2])
print(np.shape(rectangles))
return rectangles
def detectFace(self, img, threshold):
#-----------------------------#
# 归一化
#-----------------------------#
copy_img = (img.copy() - 127.5) / 127.5
origin_h, origin_w, _ = copy_img.shape
#-----------------------------#
# 计算原始输入图像
# 每一次缩放的比例
#-----------------------------#
scales = utils.calculateScales(img)
out = []
#-----------------------------#
# 粗略计算人脸框
# pnet部分
#-----------------------------#
for scale in scales:
hs = int(origin_h * scale)
ws = int(origin_w * scale)
scale_img = cv2.resize(copy_img, (ws, hs))
inputs = scale_img.reshape(1, *scale_img.shape)
ouput = self.Pnet.predict(inputs)
out.append(ouput)
image_num = len(scales)
rectangles = []
for i in range(image_num):
# 有人脸的概率
cls_prob = out[i][0][0][:, :, 1]
# 其对应的框的位置
roi = out[i][1][0]
# 取出每个缩放后图片的长宽
out_h, out_w = cls_prob.shape
out_side = max(out_h, out_w)
# 解码过程
rectangle = utils.detect_face_12net(cls_prob, roi, out_side,
1 / scales[i], origin_w,
origin_h, threshold[0])
rectangles.extend(rectangle)
# for i in range(len(rectangles)):
# bbox = rectangles[i]
# crop_img = img[int(bbox[1]):int(bbox[3]),int(bbox[0]):int(bbox[2])]
# if bbox[3]-bbox[1]>80:
# cv2.imshow("crop_img",crop_img)
# cv2.waitKey(0)
# 进行非极大抑制
rectangles = utils.NMS(rectangles, 0.7)
if len(rectangles) == 0:
return rectangles
#-----------------------------#
# 稍微精确计算人脸框
# Rnet部分
#-----------------------------#
predict_24_batch = []
for rectangle in rectangles:
crop_img = copy_img[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
scale_img = cv2.resize(crop_img, (24, 24))
predict_24_batch.append(scale_img)
predict_24_batch = np.array(predict_24_batch)
out = self.Rnet.predict(predict_24_batch)
# 可信度
cls_prob = out[0]
cls_prob = np.array(cls_prob)
# 如何调整某一张图片对应的rectangle
roi_prob = out[1]
roi_prob = np.array(roi_prob)
rectangles = utils.filter_face_24net(cls_prob, roi_prob, rectangles,
origin_w, origin_h, threshold[1])
if len(rectangles) == 0:
return rectangles
#-----------------------------#
# 计算人脸框
# onet部分
#-----------------------------#
predict_batch = []
for rectangle in rectangles:
crop_img = copy_img[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
scale_img = cv2.resize(crop_img, (48, 48))
predict_batch.append(scale_img)
predict_batch = np.array(predict_batch)
output = self.Onet.predict(predict_batch)
cls_prob = output[0]
roi_prob = output[1]
pts_prob = output[2]
rectangles = utils.filter_face_48net(cls_prob, roi_prob, pts_prob,
rectangles, origin_w, origin_h,
threshold[2])
return rectangles
def detectFace(self, img, threshold):
#-----------------------------#
# Normalization
#-----------------------------#
copy_img = (img.copy() - 127.5) / 127.5
origin_h, origin_w, _ = copy_img.shape
#-----------------------------#
# calculate the zoom proportion of
# input image
#-----------------------------#
scales = utils.calculateScales(img)
out = []
#-----------------------------#
#
# pnet part
#-----------------------------#
for scale in scales:
hs = int(origin_h * scale)
ws = int(origin_w * scale)
scale_img = cv2.resize(copy_img, (ws, hs))
inputs = scale_img.reshape(1, *scale_img.shape)
ouput = self.Pnet.predict(inputs)
out.append(ouput)
image_num = len(scales)
rectangles = []
for i in range(image_num):
# the proporation of face
cls_prob = out[i][0][0][:, :, 1]
# the position of square
roi = out[i][1][0]
# get the size of zoomed img
out_h, out_w = cls_prob.shape
out_side = max(out_h, out_w)
# encode the original size
rectangle = utils.detect_face_12net(cls_prob, roi, out_side,
1 / scales[i], origin_w,
origin_h, threshold[0])
rectangles.extend(rectangle)
# for i in range(len(rectangles)):
# bbox = rectangles[i]
# crop_img = img[int(bbox[1]):int(bbox[3]),int(bbox[0]):int(bbox[2])]
# if bbox[3]-bbox[1]>80:
# cv2.imshow("crop_img",crop_img)
# cv2.waitKey(0)
# Non-maximum suppression
rectangles = utils.NMS(rectangles, 0.7)
if len(rectangles) == 0:
return rectangles
#-----------------------------#
# get accurate position
# Rnet
#-----------------------------#
predict_24_batch = []
for rectangle in rectangles:
crop_img = copy_img[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
scale_img = cv2.resize(crop_img, (24, 24))
predict_24_batch.append(scale_img)
predict_24_batch = np.array(predict_24_batch)
out = self.Rnet.predict(predict_24_batch)
# Confidence
cls_prob = out[0]
cls_prob = np.array(cls_prob)
# Adjustment rectangle of every image
roi_prob = out[1]
roi_prob = np.array(roi_prob)
rectangles = utils.filter_face_24net(cls_prob, roi_prob, rectangles,
origin_w, origin_h, threshold[1])
if len(rectangles) == 0:
return rectangles
#-----------------------------#
#
# onet
#-----------------------------#
predict_batch = []
for rectangle in rectangles:
crop_img = copy_img[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
scale_img = cv2.resize(crop_img, (48, 48))
predict_batch.append(scale_img)
predict_batch = np.array(predict_batch)
output = self.Onet.predict(predict_batch)
cls_prob = output[0]
roi_prob = output[1]
pts_prob = output[2]
rectangles = utils.filter_face_48net(cls_prob, roi_prob, pts_prob,
rectangles, origin_w, origin_h,
threshold[2])
return rectangles
def detectFace(self, img, threshold):
#-----------------------------#
# 归一化
#-----------------------------#
copy_img = (img.copy() - 127.5) / 127.5
origin_h, origin_w, _ = copy_img.shape
#-----------------------------#
# 计算原始输入图像
# 每一次缩放的比例
#-----------------------------#
scales = utils.calculateScales(img)
out = []
#-----------------------------#
# 粗略计算人脸框
# pnet部分
#-----------------------------#
for scale in scales:
hs = int(origin_h * scale)
ws = int(origin_w * scale)
scale_img = cv2.resize(copy_img, (ws, hs))
inputs = np.expand_dims(scale_img, 0)
ouput = self.Pnet.predict(inputs)
#---------------------------------------------#
# 每次选取图像金字塔中的一张图片进行预测
# 预测结果也是一张图片的，
# 所以我们可以将对应的batch_size维度给消除掉
#---------------------------------------------#
ouput = [ouput[0][0], ouput[1][0]]
out.append(ouput)
rectangles = []
#-------------------------------------------------#
# 在这个地方我们对图像金字塔的预测结果进行循环
# 取出每张图片的种类预测和回归预测结果
#-------------------------------------------------#
for i in range(len(scales)):
#------------------------------------------------------------------#
# 为了方便理解，这里和视频上看到的不太一样
# 因为我们在上面对图像金字塔循环的时候就把batch_size维度给去掉了
#------------------------------------------------------------------#
cls_prob = out[i][0][:, :, 1]
roi = out[i][1]
#-------------------------------------#
# 取出每个缩放后图片的高宽
#-------------------------------------#
out_h, out_w = cls_prob.shape
out_side = max(out_h, out_w)
#-------------------------------------#
# 解码的过程
#-------------------------------------#
rectangle = utils.detect_face_12net(cls_prob, roi, out_side,
1 / scales[i], origin_w,
origin_h, threshold[0])
rectangles.extend(rectangle)
#-------------------------------------#
# 进行非极大抑制
#-------------------------------------#
rectangles = np.array(utils.NMS(rectangles, 0.7))
if len(rectangles) == 0:
return rectangles
#-----------------------------#
# 稍微精确计算人脸框
# Rnet部分
#-----------------------------#
predict_24_batch = []
for rectangle in rectangles:
#------------------------------------------#
# 利用获取到的粗略坐标，在原图上进行截取
#------------------------------------------#
crop_img = copy_img[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
#-----------------------------------------------#
# 将截取到的图片进行resize，调整成24x24的大小
#-----------------------------------------------#
scale_img = cv2.resize(crop_img, (24, 24))
predict_24_batch.append(scale_img)
cls_prob, roi_prob = self.Rnet.predict(np.array(predict_24_batch))
#-------------------------------------#
# 解码的过程
#-------------------------------------#
rectangles = utils.filter_face_24net(cls_prob, roi_prob, rectangles,
origin_w, origin_h, threshold[1])
if len(rectangles) == 0:
return rectangles
#-----------------------------#
# 计算人脸框
# onet部分
#-----------------------------#
predict_batch = []
for rectangle in rectangles:
#------------------------------------------#
# 利用获取到的粗略坐标，在原图上进行截取
#------------------------------------------#
crop_img = copy_img[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
#-----------------------------------------------#
# 将截取到的图片进行resize，调整成48x48的大小
#-----------------------------------------------#
scale_img = cv2.resize(crop_img, (48, 48))
predict_batch.append(scale_img)
cls_prob, roi_prob, pts_prob = self.Onet.predict(
np.array(predict_batch))
#-------------------------------------#
# 解码的过程
#-------------------------------------#
rectangles = utils.filter_face_48net(cls_prob, roi_prob, pts_prob,
rectangles, origin_w, origin_h,
threshold[2])
return rectangles
def detectFace(self, img, threshold):
#-----------------------------#
# 归一化
#-----------------------------#
copy_img = (img.copy() - 127.5) / 127.5
origin_h, origin_w, _ = copy_img.shape
# print("orgin image's shape is: ", origin_h, origin_w)
#-----------------------------#
# 计算原始输入图像
# 每一次缩放的比例
#-----------------------------#
scales = utils.calculateScales(img)
out = []
#-----------------------------#
# 粗略计算人脸框
# pnet部分
#-----------------------------#
for scale in scales:
pnet_inputs = []
pnet_outputs = []
hs = int(origin_h * scale)
ws = int(origin_w * scale)
scale_img = cv2.resize(copy_img, (ws, hs))
inputs = np.expand_dims(scale_img, 0).astype(np.float32)
pnet_inputs.append(
tritonclient.http.InferInput(self.Pnet_inputs[0], inputs.shape,
'FP32'))
pnet_inputs[0].set_data_from_numpy(inputs, binary_data=True)
pnet_outputs.append(
tritonclient.http.InferRequestedOutput(self.Pnet_outputs[0],
binary_data=True))
pnet_outputs.append(
tritonclient.http.InferRequestedOutput(self.Pnet_outputs[1],
binary_data=True))
t1 = time.time()
output = self.triton_client.infer("pnet",
inputs=pnet_inputs,
outputs=pnet_outputs)
t2 = time.time()
# print('pnet cost: {}ms'.format(1000*(t2 - t1)))
# print(output.as_numpy(self.Pnet_outputs[0]).shape)
# print(output.as_numpy(self.Pnet_outputs[1]).shape)
output = [
output.as_numpy(self.Pnet_outputs[0])[0],
output.as_numpy(self.Pnet_outputs[1])[0]
]
out.append(output)
# print(out)
rectangles = []
#-------------------------------------------------#
# 在这个地方我们对图像金字塔的预测结果进行循环
# 取出每张图片的种类预测和回归预测结果
#-------------------------------------------------#
for i in range(len(scales)):
#------------------------------------------------------------------#
# 为了方便理解，这里和视频上看到的不太一样
# 因为我们在上面对图像金字塔循环的时候就把batch_size维度给去掉了
#------------------------------------------------------------------#
cls_prob = out[i][0][:, :, 1]
roi = out[i][1]
#--------------------------------------------#
# 取出每个缩放后图片的高宽
#--------------------------------------------#
out_h, out_w = cls_prob.shape
out_side = max(out_h, out_w)
#--------------------------------------------#
# 解码的过程
#--------------------------------------------#
rectangle = utils.detect_face_12net(cls_prob, roi, out_side,
1 / scales[i], origin_w,
origin_h, threshold[0])
rectangles.extend(rectangle)
#-----------------------------------------#
# 进行非极大抑制
#-----------------------------------------#
rectangles = np.array(utils.NMS(rectangles, 0.7))
# print(rectangles)
if len(rectangles) == 0:
return rectangles
#-----------------------------------------#
# 稍微精确计算人脸框
# Rnet部分
#-----------------------------------------#
predict_24_batch = []
for rectangle in rectangles:
#--------------------------------------------#
# 利用获取到的粗略坐标，在原图上进行截取
#--------------------------------------------#
crop_img = copy_img[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
#--------------------------------------------#
# 将截取到的图片进行resize，调整成24x24的大小
#--------------------------------------------#
scale_img = cv2.resize(crop_img, (24, 24))
predict_24_batch.append(scale_img)
# print('rnet的输入: ', np.array(predict_24_batch).shape)
rnet_inputs = []
rnet_outputs = []
rnet_inputs.append(
tritonclient.http.InferInput(self.Rnet_inputs[0],
np.array(predict_24_batch).shape,
'FP32'))
rnet_inputs[0].set_data_from_numpy(np.array(predict_24_batch).astype(
np.float32),
binary_data=True)
rnet_outputs.append(
tritonclient.http.InferRequestedOutput(self.Rnet_outputs[0],
binary_data=True))
rnet_outputs.append(
tritonclient.http.InferRequestedOutput(self.Rnet_outputs[1],
binary_data=True))
t1 = time.time()
output = self.triton_client.infer("rnet",
inputs=rnet_inputs,
outputs=rnet_outputs)
t2 = time.time()
# print('rnet cost: {}ms'.format(1000*(t2-t1)))
# print(output.as_numpy(self.Rnet_outputs[0]).shape)
# print(output.as_numpy(self.Rnet_outputs[1]).shape)
cls_prob, roi_prob = output.as_numpy(
self.Rnet_outputs[0]), output.as_numpy(self.Rnet_outputs[1])
# print('cls_prob is: ')
# print(cls_prob)
# print('roi_prob is: ')
# print(roi_prob)
#-------------------------------------#
# 解码的过程
#-------------------------------------#
rectangles = utils.filter_face_24net(cls_prob, roi_prob, rectangles,
origin_w, origin_h, threshold[1])
if len(rectangles) == 0:
return rectangles
# print(rectangles)
#-----------------------------#
# 计算人脸框
# onet部分
#-----------------------------#
predict_batch = []
for rectangle in rectangles:
#------------------------------------------#
# 利用获取到的粗略坐标，在原图上进行截取
#------------------------------------------#
crop_img = copy_img[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
#-----------------------------------------------#
# 将截取到的图片进行resize，调整成48x48的大小
#-----------------------------------------------#
scale_img = cv2.resize(crop_img, (48, 48))
predict_batch.append(scale_img)
# print('onet的输入: ', np.array(predict_batch).shape)
onet_inputs = []
onet_outputs = []
onet_inputs.append(
tritonclient.http.InferInput(self.Onet_inputs[0],
np.array(predict_batch).shape,
'FP32'))
onet_inputs[0].set_data_from_numpy(np.array(predict_batch).astype(
np.float32),
binary_data=True)
onet_outputs.append(
tritonclient.http.InferRequestedOutput(self.Onet_outputs[0],
binary_data=True))
onet_outputs.append(
tritonclient.http.InferRequestedOutput(self.Onet_outputs[1],
binary_data=True))
onet_outputs.append(
tritonclient.http.InferRequestedOutput(self.Onet_outputs[2],
binary_data=True))
t1 = time.time()
output = self.triton_client.infer("onet",
inputs=onet_inputs,
outputs=onet_outputs)
t2 = time.time()
# print('onet cost: {}ms'.format(1000*(t2-t1)))
cls_prob, roi_prob, pts_prob = output.as_numpy(
self.Onet_outputs[0]), output.as_numpy(
self.Onet_outputs[1]), output.as_numpy(self.Onet_outputs[2])
#-------------------------------------#
# 解码的过程
#-------------------------------------#
# print('cls_prob:')
# print(cls_prob)
# print('roi_prob:')
# print(roi_prob)
# print('pts_prob:')
# print(pts_prob)
rectangles = utils.filter_face_48net(cls_prob, roi_prob, pts_prob,
rectangles, origin_w, origin_h,
threshold[2])
return rectangles