Non-maximum suppression. Arguments: boxes: a float numpy array of shape [n, 5], where each row is (xmin, ymin, xmax, ymax

Transform bounding boxes to be more like true bounding boxes. 'offsets' is one of the outputs of the nets. Arguments: bboxes: a f

Function: ---------- apply affine transform 'trans' to uv Parameters: ---------- @trans: 3x3 np.array

Convert bounding boxes to a square form. Arguments: bboxes: a float numpy array of shape [n, 5]. Returns: a float nump

Cut out boxes from the image. Arguments: bounding_boxes: a float numpy array of shape [n, 5]. img: an instance of PIL.Image.

Preprocessing step before feeding the network. Arguments: img: a float numpy array of shape [h, w, c]. Returns: a floa

Upsample and add two feature maps. Args: x: (Variable) top feature map to be upsampled. y: (Variable) lateral feature m

Arguments: image: an instance of PIL.Image. min_face_size: a float number. thresholds: a list of leng

Function: ---------- get reference 5 key points according to crop settings: 0. Set default crop_size: if def

Function: ---------- Find Similarity Transform Matrix 'trans': u = src_pts[:, 0] v = src_pts[:, 1]

Run P-Net, generate bounding boxes, and do NMS. Arguments: image: an instance of PIL.Image. net: an instance of pytorch's nn.

Function: ---------- apply affine transform 'trans' to uv Parameters: ---------- @src_img: 3x3 np.array

Constructs a ir-101 model.

Generate bounding boxes at places where there is probably a face. Arguments: probs: a float numpy array of shape [n, m].

:param filepath: str :return: PIL Image

This equation is exactly copied from the website below: https://clouard.users.greyc.fr/Pantheon/experiments/rescaling/index-en.html#bicubic

Yield successive n-sized chunks from lst.

Yield successive n-sized chunks from lst.

Crop boxes that are too big and get coordinates with respect to cutouts. Arguments: bboxes: a float numpy array of shape [n, 5],

Function: ---------- Convert Transform Matrix 'trans' into 'cv2_trans' which could be directly used by cv2.warpAffine():

Function: ---------- get affine transform matrix 'tfm' from src_pts to dst_pts Parameters: ---------- @src_pts:

get landmark with dlib :return: np.array shape=(68, 2)

Function: ---------- Find Similarity Transform Matrix 'cv2_trans' which could be directly used by cv2.warpAffine():

:param d_model: dimension of the model :param height: height of the positions :param width: width of the positions :return: d_model*h

Function: ---------- apply the inverse of affine transform 'trans' to uv Parameters: ---------- @trans: 3x3 n