def detect_pnet(im, min_face_size, scale_factor, thresh):
"""
通过pnet筛选box和landmark
参数：
im:输入图像[h,2,3]
"""
net_size = 12
# 人脸和输入图像的比率
current_scale = float(net_size) / min_face_size
im_resized = processed_image(im, current_scale)
_, current_height, current_width = im_resized.shape
all_boxes = list()
# 图像金字塔
while min(current_height, current_width) > net_size:
# 类别和box
cls_cls_map, reg = predict_pnet(im_resized)
boxes = generate_bbox(cls_cls_map[1, :, :], reg, current_scale, thresh)
current_scale *= scale_factor # 继续缩小图像做金字塔
im_resized = processed_image(im, current_scale)
_, current_height, current_width = im_resized.shape
if boxes.size == 0:
continue
# 非极大值抑制留下重复低的box
keep = py_nms(boxes[:, :5], 0.5, mode='Union')
boxes = boxes[keep]
all_boxes.append(boxes)
if len(all_boxes) == 0:
return None
all_boxes = np.vstack(all_boxes)
# 将金字塔之后的box也进行非极大值抑制
keep = py_nms(all_boxes[:, 0:5], 0.7, mode='Union')
all_boxes = all_boxes[keep]
# box的长宽
bbw = all_boxes[:, 2] - all_boxes[:, 0] + 1
bbh = all_boxes[:, 3] - all_boxes[:, 1] + 1
# 对应原图的box坐标和分数
boxes_c = np.vstack([all_boxes[:, 0] + all_boxes[:, 5] * bbw,
all_boxes[:, 1] + all_boxes[:, 6] * bbh,
all_boxes[:, 2] + all_boxes[:, 7] * bbw,
all_boxes[:, 3] + all_boxes[:, 8] * bbh,
all_boxes[:, 4]])
boxes_c = boxes_c.T
return boxes_c
def detect_rnet(im, dets, thresh):
"""通过rent选择box
参数：
im：输入图像
dets:pnet选择的box，是相对原图的绝对坐标
返回值：
box绝对坐标
"""
h, w, c = im.shape
# 将pnet的box变成包含它的正方形，可以避免信息损失
dets = convert_to_square(dets)
dets[:, 0:4] = np.round(dets[:, 0:4])
# 调整超出图像的box
[dy, edy, dx, edx, y, ey, x, ex, tmpw, tmph] = pad(dets, w, h)
delete_size = np.ones_like(tmpw) * 20
ones = np.ones_like(tmpw)
zeros = np.zeros_like(tmpw)
num_boxes = np.sum(
np.where((np.minimum(tmpw, tmph) >= delete_size), ones, zeros))
cropped_ims = np.zeros((num_boxes, 3, 24, 24), dtype=np.float32)
if int(num_boxes) == 0:
print('P模型检测结果为空！')
return None, None
for i in range(int(num_boxes)):
# 将pnet生成的box相对与原图进行裁剪，超出部分用0补
if tmph[i] < 20 or tmpw[i] < 20:
continue
tmp = np.zeros((tmph[i], tmpw[i], 3), dtype=np.uint8)
try:
tmp[dy[i]:edy[i] + 1, dx[i]:edx[i] + 1, :] = im[y[i]:ey[i] + 1,
x[i]:ex[i] + 1, :]
img = cv2.resize(tmp, (24, 24))
img = img.transpose((2, 0, 1))
img = (img - 127.5) / 128
cropped_ims[i, :, :, :] = img
except:
continue
cls_scores, reg = predict_rnet(cropped_ims)
cls_scores = cls_scores[:, 1]
keep_inds = np.where(cls_scores > thresh)[0]
if len(keep_inds) > 0:
boxes = dets[keep_inds]
boxes[:, 4] = cls_scores[keep_inds]
reg = reg[keep_inds]
else:
return None, None
keep = py_nms(boxes, 0.6, mode='Union')
boxes = boxes[keep]
# 对pnet截取的图像的坐标进行校准，生成rnet的人脸框对于原图的绝对坐标
boxes_c = calibrate_box(boxes, reg[keep])
return boxes, boxes_c
def predict(self, image):
org_image = np.copy(image)
org_h, org_w, _ = org_image.shape
original_image_size = org_image.shape[:2]
image_data = utils.image_preporcess(image,
[self.input_size, self.input_size])
image_data = image_data[np.newaxis, ...]
detections = self.sess.run(self.det,
feed_dict={self.input_data: image_data})
detections = utils.post_process(detections, original_image_size,
[cfg.input_image_h, cfg.input_image_w],
cfg.down_ratio, cfg.score_threshold)
bboxes = []
scores = [0]
classes = [0]
if cfg.use_nms:
cls_in_img = list(set(detections[:, 5]))
results = []
for c in cls_in_img:
cls_mask = (detections[:, 5] == c)
classified_det = detections[cls_mask]
classified_bboxes = classified_det[:, :4]
classified_scores = classified_det[:, 4]
inds = utils.py_nms(classified_bboxes,
classified_scores,
max_boxes=50,
iou_thresh=0.5)
results.extend(classified_det[inds])
results = np.asarray(results)
if len(results) != 0:
bboxes = results[:, 0:4]
scores = results[:, 4]
classes = results[:, 5]
#bboxes_draw_on_img(original_image, classes, scores, bboxes, class_names)
else:
bboxes = detections[:, 0:4]
scores = detections[:, 4]
classes = detections[:, 5]
#bboxes_draw_on_img(original_image, classes, scores, bboxes, class_names)
return bboxes, scores, classes
def detect_onet(im, dets, thresh):
"""将onet的选框继续筛选基本和rnet差不多但多返回了landmark"""
h, w, c = im.shape
dets = convert_to_square(dets)
dets[:, 0:4] = np.round(dets[:, 0:4])
[dy, edy, dx, edx, y, ey, x, ex, tmpw, tmph] = pad(dets, w, h)
num_boxes = dets.shape[0]
cropped_ims = np.zeros((num_boxes, 3, 48, 48), dtype=np.float32)
for i in range(num_boxes):
tmp = np.zeros((tmph[i], tmpw[i], 3), dtype=np.uint8)
tmp[dy[i]:edy[i] + 1, dx[i]:edx[i] + 1, :] = im[y[i]:ey[i] + 1,
x[i]:ex[i] + 1, :]
img = cv2.resize(tmp, (48, 48), interpolation=cv2.INTER_LINEAR)
img = img.transpose((2, 0, 1))
img = (img - 127.5) / 128
cropped_ims[i, :, :, :] = img
cls_scores, reg, landmark = predict_onet(cropped_ims)
cls_scores = cls_scores[:, 1]
keep_inds = np.where(cls_scores > thresh)[0]
if len(keep_inds) > 0:
boxes = dets[keep_inds]
boxes[:, 4] = cls_scores[keep_inds]
reg = reg[keep_inds]
landmark = landmark[keep_inds]
else:
return None, None
w = boxes[:, 2] - boxes[:, 0] + 1
h = boxes[:, 3] - boxes[:, 1] + 1
landmark[:, 0::2] = (np.tile(w, (5, 1)) * landmark[:, 0::2].T +
np.tile(boxes[:, 0], (5, 1)) - 1).T
landmark[:, 1::2] = (np.tile(h, (5, 1)) * landmark[:, 1::2].T +
np.tile(boxes[:, 1], (5, 1)) - 1).T
boxes_c = calibrate_box(boxes, reg)
keep = py_nms(boxes_c, 0.6, mode='Minimum')
boxes_c = boxes_c[keep]
landmark = landmark[keep]
return boxes_c, landmark
detections = sess.run(det, feed_dict={inputs: image_data})
detections = post_process(detections, original_image_size,
[cfg.input_image_h, cfg.input_image_w],
cfg.down_ratio, cfg.score_threshold)
print('Inferencce took %.1f ms (%.2f fps)' %
((time.time() - t0) * 1000, 1 / (time.time() - t0)))
if cfg.use_nms:
cls_in_img = list(set(detections[:, 5]))
results = []
for c in cls_in_img:
cls_mask = (detections[:, 5] == c)
classified_det = detections[cls_mask]
classified_bboxes = classified_det[:, :4]
classified_scores = classified_det[:, 4]
inds = py_nms(classified_bboxes,
classified_scores,
max_boxes=50,
iou_thresh=0.5)
results.extend(classified_det[inds])
results = np.asarray(results)
print("results is", results)
if len(results) != 0:
bboxes = results[:, 0:4]
scores = results[:, 4]
classes = results[:, 5]
bboxes_draw_on_img(original_image, classes, scores, bboxes,
class_names)
else:
bboxes = detections[:, 0:4]
scores = detections[:, 4]
classes = detections[:, 5]
