Replace Conv2d with a depthwise Conv2d and Pointwise Conv2d.

Replace Conv2d with a depthwise Conv2d and Pointwise Conv2d.

Input: - img: gray or RGB - bbox: type of BBox - landmark: reproject landmark of (5L, 2L) Output: - img marked with lan

Dispatch to either CPU or GPU NMS implementations.

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

Compute the areas of rectangles given two corners. Args: left_top (N, 2): left top corner. right_bottom (N, 2): right bottom corn

Compute the areas of rectangles given two corners. Args: left_top (N, 2): left top corner. right_bottom (N, 2): right bottom corn

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

Return intersection-over-union (Jaccard index) of boxes. Args: boxes0 (N, 4): ground truth boxes. boxes1 (N or 1, 4): predicted b

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

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

Arguments: image: an instance of PIL.Image. min_face_size: a float number. thresholds: a list of length 3. nms_th

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

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

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

Old style model is stored with all names of parameters sharing common prefix 'module.'

Old style model is stored with all names of parameters sharing common prefix 'module.'

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

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():

Decode locations from predictions using priors to undo the encoding we did for offset regression at train time. Args: loc (tensor): lo

Decode locations from predictions using priors to undo the encoding we did for offset regression at train time. Args: loc (tensor): lo

Decode landm from predictions using priors to undo the encoding we did for offset regression at train time. Args: pre (tensor): landm

Encode the variances from the priorbox layers into the ground truth boxes we have matched (based on jaccard overlap) with the prior boxes. Arg

Encode the variances from the priorbox layers into the ground truth boxes we have matched (based on jaccard overlap) with the prior boxes. Arg

Encode the variances from the priorbox layers into the ground truth boxes we have matched (based on jaccard overlap) with the prior boxes. Arg

Function: ---------- get affine transform matrix 'tfm' from src_pts to dst_pts Parameters: ---------- @src_pts: Kx2 n

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

Args: box_scores (N, 5): boxes in corner-form and probabilities. iou_threshold: intersection over union threshold. top_k

We resize both tensors to [A,B,2] without new malloc: [A,2] -> [A,1,2] -> [A,B,2] [B,2] -> [1,B,2] -> [A,B,2] Then we compute the area of

We resize both tensors to [A,B,2] without new malloc: [A,2] -> [A,1,2] -> [A,B,2] [B,2] -> [1,B,2] -> [A,B,2] Then we compute the area of

Return intersection-over-union (Jaccard index) of boxes. Args: boxes0 (N, 4): ground truth boxes. boxes1 (N or 1, 4): predicted b

Compute the jaccard overlap of two sets of boxes. The jaccard overlap is simply the intersection over union of two boxes. Here we operate on

Compute the jaccard overlap of two sets of boxes. The jaccard overlap is simply the intersection over union of two boxes. Here we operate on

Compute the jaccard overlap of two sets of boxes. The jaccard overlap is simply the intersection over union of two boxes. E.g.: A ∩ B

Utility function for computing log_sum_exp while determining This will be used to determine unaveraged confidence loss across all examples in