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

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: ---------- 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]

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

人脸对比 :param img: :return:

人脸对比 :param img: :return:

将超出图像的box进行处理 参数： bboxes:人脸框 w,h:图像长宽 返回值： dy, dx : 为调整后的box的左上角坐标相对于原box左上角的坐标 edy, edx : n为调整后的box右下角相对原box左上角的相对坐标

将超出图像的box进行处理 参数： bboxes:人脸框 w,h:图像长宽 返回值： dy, dx : 为调整后的box的左上角坐标相对于原box左上角的坐标 edy, edx : n为调整后的box右下角相对原box左上角的相对坐标

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

用于更新人脸数据库 :return:

Get a block through a string notation of arguments. Args: block_string (str): A string notation of arguments.

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

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

Computes the precision@k for the specified values of k

Computes the precision@k for the specified values of k

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

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():

Make a vector of weights for each image in the dataset, based on class frequency. The returned vector of weights can be used

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

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

Drop connect. Args: input (tensor: BCWH): Input of this structure. p (float: 0.0~1.0): Probability of drop connection. tr

use convolution layer to extract feature . Args: inputs (tensor): Input tensor. Returns: Output of the final

create an efficientnet model according to name. Args: model_name (str): Name for efficientnet. in_channels (int): Inp

Create a pyplot plot and save to buffer.

Create a pyplot plot and save to buffer.

得到对应原图的box坐标，分类分数，box偏移量

得到对应原图的box坐标，分类分数，box偏移量

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

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

Obtain height and width from x. Args: x (int, tuple or list): Data size. Returns: size: A tuple or list (H,W).

Loads pretrained weights from weights path or download using url. Args: model (Module): The whole model of efficientnet. model_na

Make a vector of weights for each image in the dataset, based on class frequency. The returned vector of weights can be used

Make a vector of weights for each image in the dataset, based on class frequency. The returned vector of weights can be used

Generate a set of distortions. Args: N: Number of augmentation transformations to apply sequentially. N is len(transforms)/