def rnet_boxes(img,
rnet,
bounding_boxes,
thresholds=THRESHOLDS,
nms_thresholds=NMS_THRESHOLDS,
show_boxes=True):
rnet.eval()
img_boxes = get_image_boxes(bounding_boxes, img, size=24)
img_boxes = torch.FloatTensor(img_boxes)
img_boxes = img_boxes.to(
torch.device('cuda' if torch.cuda.is_available() else 'cpu'))
output = rnet(img_boxes)
probs = output[0].data.cpu().numpy() # shape [n_boxes, 1]
offsets = output[1].data.cpu().numpy() # shape [n_boxes, 4]
keep = np.where(probs[:, 0] > thresholds[1])[0]
bounding_boxes = bounding_boxes[keep]
bounding_boxes[:, 4] = probs[keep, 0].reshape((-1, ))
offsets = offsets[keep]
keep = nms(bounding_boxes, nms_thresholds[1])
bounding_boxes = bounding_boxes[keep]
bounding_boxes = calibrate_box(bounding_boxes, offsets[keep])
bounding_boxes = convert_to_square(bounding_boxes)
bounding_boxes[:, 0:4] = np.round(bounding_boxes[:, 0:4])
if show_boxes: show_bboxes(img, bounding_boxes, []).show()
return bounding_boxes
def onet_test(args, img_path):
img = load_img(img_path)
net = load_net(args, 'pnet')
output = net((transforms.ToTensor()(img.resize(
(12, 12), Image.BILINEAR))).unsqueeze(0))
print('prob:', output[0])
show_bboxes(img, [[(250 * t.item() + 250 * (i > 1))
for i, t in enumerate(output[1][0])]]).show()
def pnet_boxes(img, pnet, min_face_size=MIN_FACE_SIZE, thresholds=THRESHOLDS, nms_thresholds=NMS_THRESHOLDS,
show_boxes=True):
pnet.eval()
width, height = img.size
min_length = min(height, width)
# print('img min_length is {}'.format(min_length))
min_detection_size = 12
factor = 0.707 # sqrt(0.5)
scales = []
# min_face_size 哪来的？
m = min_detection_size / min_face_size
# 缩放原图使得最小脸尺寸为12pix
min_length *= m
# 将图片从最小脸为12pix到整张图为12pix，保存对应的缩放比例，都为小于1的数？
factor_count = 0
while min_length > min_detection_size:
scales.append(m * factor ** factor_count)
min_length *= factor
factor_count += 1
# STAGE 1
bounding_boxes = []
for s in scales: # run P-Net on different scales
boxes = run_first_stage(img, pnet, scale=s, threshold=thresholds[0])
bounding_boxes.append(boxes)
# bounding_boxes shape:[scales,boxes_num_each_sale,5]
# 把每个scale找到的框框全部打开堆在一起
# [total_boxes_num, 5] 是list
bounding_boxes = [i for i in bounding_boxes if i is not None]
# print(bounding_boxes)
# bounding_boxes = np.array(bounding_boxes)
# print(bounding_boxes.shape, img.size)
try:
_ = bounding_boxes[0]
# print('bounding_boxes:{}'.format(len(bounding_boxes)))
# print('bounding_boxes[0]:{}'.format(len(bounding_boxes[0])))
except Exception:
print(bounding_boxes)
img.show()
if len(bounding_boxes) == 0:
return None
bounding_boxes = np.vstack(bounding_boxes)
# print(bounding_boxes.shape)
keep = nms(bounding_boxes[:, 0:5], nms_thresholds[0])
bounding_boxes = bounding_boxes[keep]
# print('bounding_boxes:{}'.format(bounding_boxes[:, 4] > 0.5))
# 根据 w、h 对 x1,y1,x2,y2 的位置进行微调
bounding_boxes = calibrate_box(bounding_boxes[:, 0:5], bounding_boxes[:, 5:])
# 将检测出的框转化成矩形
bounding_boxes = convert_to_square(bounding_boxes)
bounding_boxes[:, 0:4] = np.round(bounding_boxes[:, 0:4])
# print('bounding_boxes:{}'.format(bounding_boxes[:, 4] > 0.5))
# print('bounding_boxes:', len(bounding_boxes), bounding_boxes)
if show_boxes: show_bboxes(img, bounding_boxes, []).show()
return bounding_boxes
def onet_boxes(img,
onet,
bounding_boxes,
thresholds=THRESHOLDS,
nms_thresholds=NMS_THRESHOLDS,
show_boxes=True):
onet.eval()
img_boxes = get_image_boxes(bounding_boxes, img, size=48)
if len(img_boxes) == 0:
return [], []
img_boxes = torch.FloatTensor(img_boxes)
img_boxes = img_boxes.to(
torch.device('cuda' if torch.cuda.is_available() else 'cpu'))
output = onet(img_boxes)
probs = output[0].data.cpu().numpy() # shape [n_boxes, 1]
offsets = output[1].data.cpu().numpy() # shape [n_boxes, 4]
landmarks = output[2].data.cpu().numpy() # shape [n_boxes, 10]
keep = np.where(probs[:, 0] > thresholds[2])[0]
bounding_boxes = bounding_boxes[keep]
# 用更大模型的置信度对原置信度进行更新
bounding_boxes[:, 4] = probs[keep, 0].reshape((-1, ))
offsets = offsets[keep]
landmarks = landmarks[keep]
# compute landmark points
width = bounding_boxes[:, 2] - bounding_boxes[:, 0] + 1.0
height = bounding_boxes[:, 3] - bounding_boxes[:, 1] + 1.0
xmin, ymin = bounding_boxes[:, 0], bounding_boxes[:, 1]
# print('width:{},\nheight:{},\nxmin:{},\nymin:{}\n'.format(width, height, xmin, ymin))
# landmark[,前5个为x，后5个为y]
# 在左上角坐标的基础上，通过 w，h 确定脸各关键点的坐标。
landmarks_pixel = np.zeros(landmarks.shape)
landmarks_pixel[:, 0:5] = (
np.expand_dims(xmin, 1) +
np.expand_dims(width, 1) * landmarks[:, 0::2]).copy()
landmarks_pixel[:, 5:10] = (
np.expand_dims(ymin, 1) +
np.expand_dims(height, 1) * landmarks[:, 1::2]).copy()
# for i in landmarks:print(i)
bounding_boxes = calibrate_box(bounding_boxes, offsets)
keep = nms(bounding_boxes, nms_thresholds[2], mode='min')
bounding_boxes = bounding_boxes[keep]
landmarks_pixel = landmarks_pixel[keep]
if show_boxes: show_bboxes(img, bounding_boxes, landmarks_pixel).show()
return bounding_boxes, landmarks_pixel