def run_first_stage(image, net, scale, threshold):
"""Run P-Net, generate bounding boxes, and do NMS.
Arguments:
image: an instance of PIL.Image.
net: an instance of pytorch's nn.Module, P-Net.
scale: a float number,
scale width and height of the image by this number.
threshold: a float number,
threshold on the probability of a face when generating
bounding boxes from predictions of the net.
Returns:
a float numpy array of shape [n_boxes, 9],
bounding boxes with scores and offsets (4 + 1 + 4).
"""
with torch.no_grad():
# scale the image and convert it to a float array
width, height = image.size
sw, sh = math.ceil(width * scale), math.ceil(height * scale)
img = image.resize((sw, sh), Image.BILINEAR)
img = np.asarray(img, 'float32')
img = Variable(torch.FloatTensor(_preprocess(img)))
output = net(img)
probs = output[1].data.numpy()[0, 1, :, :]
offsets = output[0].data.numpy()
# probs: probability of a face at each sliding window
# offsets: transformations to true bounding boxes
boxes = _generate_bboxes(probs, offsets, scale, threshold)
if len(boxes) == 0:
return None
keep = nms(boxes[:, 0:5], overlap_threshold=0.5)
return boxes[keep]
def run_first_stage(image, net, scale, threshold):
"""
Run P-Net, generate bounding boxes, and do NMS.
"""
width, height = image.size
sw, sh = math.ceil(width * scale), math.ceil(height * scale)
img = image.resize((sw, sh), Image.BILINEAR)
img = np.asarray(img, 'float32')
img = torch.FloatTensor(_preprocess(img))
output = net(img)
probs = output[1].data.numpy()[0, 1, :, :]
offsets = output[0].data.numpy()
boxes = _generate_bboxes(probs, offsets, scale, threshold)
if len(boxes) == 0:
return None
keep = nms(boxes[:, 0:5], overlap_threshold=0.5)
return boxes[keep]
def detect_faces(image,
min_face_size=20.0,
thresholds=[0.6, 0.7, 0.8],
nms_thresholds=[0.7, 0.7, 0.7]):
"""
Arguments:
image: an instance of PIL.Image.
min_face_size: a float number.
thresholds: a list of length 3.
nms_thresholds: a list of length 3.
Returns:
two float numpy arrays of shapes [n_boxes, 4] and [n_boxes, 10],
bounding boxes and facial landmarks.
"""
with torch.no_grad():
# LOAD MODELS
pnet = PNet().to(device)
rnet = RNet().to(device)
onet = ONet().to(device)
onet.eval()
# BUILD AN IMAGE PYRAMID
width, height = image.size
min_length = min(height, width)
min_detection_size = 12
factor = 0.707 # sqrt(0.5)
# scales for scaling the image
scales = []
# scales the image so that
# minimum size that we can detect equals to
# minimum face size that we want to detect
m = min_detection_size / min_face_size
min_length *= m
factor_count = 0
while min_length > min_detection_size:
scales.append(m * factor**factor_count)
min_length *= factor
factor_count += 1
# STAGE 1
# it will be returned
bounding_boxes = []
# run P-Net on different scales
for s in scales:
boxes = run_first_stage(image,
pnet,
scale=s,
threshold=thresholds[0])
bounding_boxes.append(boxes)
# collect boxes (and offsets, and scores) from different scales
bounding_boxes = [i for i in bounding_boxes if i is not None]
bounding_boxes = np.vstack(bounding_boxes)
keep = nms(bounding_boxes[:, 0:5], nms_thresholds[0])
bounding_boxes = bounding_boxes[keep]
# use offsets predicted by pnet to transform bounding boxes
bounding_boxes = calibrate_box(bounding_boxes[:, 0:5],
bounding_boxes[:, 5:])
# shape [n_boxes, 5]
bounding_boxes = convert_to_square(bounding_boxes)
bounding_boxes[:, 0:4] = np.round(bounding_boxes[:, 0:4])
# STAGE 2
img_boxes = get_image_boxes(bounding_boxes, image, size=24)
img_boxes = Variable(torch.FloatTensor(img_boxes).to(device))
output = rnet(img_boxes)
offsets = output[0].data.cpu().numpy() # shape [n_boxes, 4]
probs = output[1].data.cpu().numpy() # shape [n_boxes, 2]
keep = np.where(probs[:, 1] > thresholds[1])[0]
bounding_boxes = bounding_boxes[keep]
bounding_boxes[:, 4] = probs[keep, 1].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])
# STAGE 3
img_boxes = get_image_boxes(bounding_boxes, image, size=48)
if len(img_boxes) == 0:
return [], []
img_boxes = Variable(torch.FloatTensor(img_boxes).to(device))
output = onet(img_boxes)
landmarks = output[0].data.cpu().numpy() # shape [n_boxes, 10]
offsets = output[1].data.cpu().numpy() # shape [n_boxes, 4]
probs = output[2].data.cpu().numpy() # shape [n_boxes, 2]
keep = np.where(probs[:, 1] > thresholds[2])[0]
bounding_boxes = bounding_boxes[keep]
bounding_boxes[:, 4] = probs[keep, 1].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]
landmarks[:, 0:5] = np.expand_dims(
xmin, 1) + np.expand_dims(width, 1) * landmarks[:, 0:5]
landmarks[:, 5:10] = np.expand_dims(
ymin, 1) + np.expand_dims(height, 1) * landmarks[:, 5:10]
bounding_boxes = calibrate_box(bounding_boxes, offsets)
keep = nms(bounding_boxes, nms_thresholds[2], mode='min')
bounding_boxes = bounding_boxes[keep]
landmarks = landmarks[keep]
return bounding_boxes, landmarks
def detect_faces(image,
min_face_size=20.0,
thresholds=[0.6, 0.7, 0.8],
nms_thresholds=[0.7, 0.7, 0.7]):
pnet, rnet, onet = load_trained_weights()
width, height = image.size
min_length = min(height, width)
min_detection_size = 12
factor = math.sqrt(0.5)
scales = []
m = min_detection_size / min_face_size
min_length *= m
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(image, pnet, scale=s, threshold=thresholds[0])
bounding_boxes.append(boxes)
bounding_boxes = [i for i in bounding_boxes if i is not None]
bounding_boxes = np.vstack(bounding_boxes)
keep = nms(bounding_boxes[:, 0:5], nms_thresholds[0])
bounding_boxes = bounding_boxes[keep]
bounding_boxes = calibrate_box(bounding_boxes[:, 0:5], bounding_boxes[:,
5:])
bounding_boxes = convert_to_square(bounding_boxes)
bounding_boxes[:, 0:4] = np.round(bounding_boxes[:, 0:4])
# STAGE 2
img_boxes = get_image_boxes(bounding_boxes, image, size=24)
img_boxes = torch.FloatTensor(img_boxes)
output = rnet(img_boxes)
offsets = output[0].data.numpy() # shape [n_boxes, 4]
probs = output[1].data.numpy() # shape [n_boxes, 2]
keep = np.where(probs[:, 1] > thresholds[1])[0]
bounding_boxes = bounding_boxes[keep]
bounding_boxes[:, 4] = probs[keep, 1].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])
# STAGE 3
img_boxes = get_image_boxes(bounding_boxes, image, size=48)
if len(img_boxes) == 0:
return [], []
img_boxes = torch.FloatTensor(img_boxes)
output = onet(img_boxes)
landmarks = output[0].data.numpy() # shape [n_boxes, 10]
offsets = output[1].data.numpy() # shape [n_boxes, 4]
probs = output[2].data.numpy() # shape [n_boxes, 2]
keep = np.where(probs[:, 1] > thresholds[2])[0]
bounding_boxes = bounding_boxes[keep]
bounding_boxes[:, 4] = probs[keep, 1].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]
landmarks[:, 0:5] = np.expand_dims(
xmin, 1) + np.expand_dims(width, 1) * landmarks[:, 0:5]
landmarks[:, 5:10] = np.expand_dims(
ymin, 1) + np.expand_dims(height, 1) * landmarks[:, 5:10]
bounding_boxes = calibrate_box(bounding_boxes, offsets)
keep = nms(bounding_boxes, nms_thresholds[2], mode='min')
bounding_boxes = bounding_boxes[keep]
landmarks = landmarks[keep]
return bounding_boxes, landmarks