Functions — github.com/cunjian/pytorch_face

hub / github.com/cunjian/pytorch_face_landmark / functions

Functions362 in github.com/cunjian/pytorch_face_landmark

⨍ Functions 362◇ Types & classes 104

Method__init__

(self)

vision/transforms/transforms.py:366

Method__init__

(self, mean)

vision/transforms/transforms.py:457

Method__init__

(self, swaps)

vision/transforms/transforms.py:502

Method__init__

(self)

vision/transforms/transforms.py:521

Method__init__

(self, in_planes, out_planes, kernel_size, stride=1, padding=0, dilation=1, groups=1, relu=True, bn=True)

vision/nn/mb_tiny_RFB.py:8

Method__init__

(self, num_classes=2)

vision/nn/mb_tiny_RFB.py:74

Method__init__

(self, num_classes=2)

vision/nn/mb_tiny.py:7

Method__init__

Implement SSD Multibox Loss. Basically, Multibox loss combines classification loss and Smooth L1 regression loss.

vision/nn/multibox_loss.py:9

Method__init__

Dataset for VOC data. Args: root: the root of the VOC2007 or VOC2012 dataset, the directory contains the following sub-directories

vision/datasets/voc_dataset.py:12

Method__init__

Args: size: the size the of final image. mean: mean pixel value per channel.

vision/ssd/data_preprocessing.py:5

Method__init__

(self, size, mean=0.0, std=1.0)

vision/ssd/data_preprocessing.py:37

Method__init__

(self, size, mean=0.0, std=1.0)

vision/ssd/data_preprocessing.py:51

Method__init__

(self, net, size, mean=0.0, std=1.0, nms_method=None, iou_threshold=0.3, filter_threshold=0.0

vision/ssd/predictor.py:9

Method__init__

Compose a SSD model using the given components.

vision/ssd/ssd.py:15

Method__init__

(self, center_form_priors, center_variance, size_variance, iou_threshold)

vision/ssd/ssd.py:145

(self, inp, oup, stride, use_res_connect, expand_ratio=6)

models/pfld_compressed.py:29

Method__init__

(self, inp, oup, k, s, p, dw=False, linear=False)

(self, in_c, out_c, kernel=(1, 1), stride=(1, 1), padding=(0, 0), groups=1)

models/mobilefacenet.py:18

Method__init__

(self, in_c, out_c, kernel=(1, 1), stride=(1, 1), padding=(0, 0), groups=1)

models/mobilefacenet.py:30

Method__init__

(self, in_c, out_c, residual = False, kernel=(3, 3), stride=(2, 2), padding=(1, 1), groups=1)

models/mobilefacenet.py:40

Method__init__

(self, c, num_block, groups, kernel=(3, 3), stride=(1, 1), padding=(1, 1))

models/mobilefacenet.py:59

Method__init__

(self, embedding_size)

models/mobilefacenet.py:69

Method__init__

(self, input_size, embedding_size = 512, output_name = "GDC")

models/mobilefacenet.py:105

Method__len__

(self)

Retinaface/data/wider_face.py:37

Method__len__

(self)

vision/datasets/voc_dataset.py:77

Method__str__

(self)

utils/matlab_cp2tform.py:7

Method__str__

(self)

utils/align_trans.py:20

Function_expand

(image, boxes, fill, p)

Retinaface/data/data_augment.py:141

Method_sigint_handler

(self, signum, frame)

utils/progress/progress/helpers.py:89

Function_xavier_init_

(m: nn.Module)

vision/ssd/ssd.py:164

Functionaccuracy

Computes the precision@k for the specified values of k

utils/eval.py:6

Functionassign_priors

Assign ground truth boxes and targets to priors. Args: gt_boxes (num_targets, 4): ground truth boxes. gt_labels (num_targets): la

vision/utils/box_utils.py:101

Methodbuild_extensions

(self)

FaceBoxes/utils/build.py:37

Functioncenter_form_to_corner_form

(locations)

vision/utils/box_utils_numpy.py:73

Functioncenter_form_to_corner_form

(locations)

vision/utils/box_utils.py:156

Functioncenter_size

Convert prior_boxes to (cx, cy, w, h) representation for comparison to center-size form ground truth data. Args: boxes: (tensor) poin

FaceBoxes/utils/box_utils.py:19

Functioncenter_size

Convert prior_boxes to (cx, cy, w, h) representation for comparison to center-size form ground truth data. Args: boxes: (tensor) poin

Retinaface/utils/box_utils.py:17

Functioncheck_bbox

Check whether bbox is out of the range of the image

common/utils.py:144

Methodclear

(self)

FaceBoxes/utils/timer.py:38

Functioncolorize

Converts a one-channel grayscale image to a color heatmap image

utils/visualize.py:21

Functionconv_1x1_bn

(inp, oup)

models/pfld_compressed.py:21

Methodconv_bn

(inp, oup, stride)

vision/nn/mb_tiny_RFB.py:78

Methodconv_bn

(inp, oup, stride)

vision/nn/mb_tiny.py:11

Methodconv_dw

(inp, oup, stride)

vision/nn/mb_tiny_RFB.py:85

Functionconvert_boxes_to_locations

(center_form_boxes, center_form_priors, center_variance, size_variance)

vision/utils/box_utils_numpy.py:30

Functionconvert_boxes_to_locations

(center_form_boxes, center_form_priors, center_variance, size_variance)

vision/utils/box_utils.py:58

Functionconvert_locations_to_boxes

Convert regressional location results of SSD into boxes in the form of (center_x, center_y, h, w). The conversion: $$predicted\_center *

vision/utils/box_utils_numpy.py:4

Functionconvert_locations_to_boxes

Convert regressional location results of SSD into boxes in the form of (center_x, center_y, h, w). The conversion: $$predicted\_center *

vision/utils/box_utils.py:32

Functioncorner_form_to_center_form

(boxes)

vision/utils/box_utils_numpy.py:78

Functioncorner_form_to_center_form

(boxes)

vision/utils/box_utils.py:161

Functioncreate_Mb_Tiny_RFB_fd

(num_classes, is_test=False, device="cuda")

vision/ssd/mb_tiny_RFB_fd.py:20

Functioncreate_Mb_Tiny_RFB_fd_predictor

(net, candidate_size=200, nms_method=None, sigma=0.5, device=None)

vision/ssd/mb_tiny_RFB_fd.py:56

Functioncreate_mb_tiny_fd

(num_classes, is_test=False, device="cuda")

vision/ssd/mb_tiny_fd.py:20

Functioncreate_mb_tiny_fd_predictor

(net, candidate_size=200, nms_method=None, sigma=0.5, device=None)

vision/ssd/mb_tiny_fd.py:56

Functiondefine_img_size

(size)

vision/ssd/config/fd_config.py:18

Functiondetection_collate

Custom collate fn for dealing with batches of images that have a different number of associated object annotations (bounding boxes). Argument

Retinaface/data/wider_face.py:79

FunctiondrawLandmark

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

common/utils.py:34

FunctiondrawLandmark_Attribute

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

common/utils.py:63

FunctiondrawLandmark_only

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

common/utils.py:87

Methodelapsed

(self)

utils/progress/progress/__init__.py:46

Methodelapsed_td

(self)

utils/progress/progress/__init__.py:50

Methodeta

(self)

utils/progress/progress/__init__.py:90

Methodeta_td

(self)

utils/progress/progress/__init__.py:94

Functionfind_in_path

Find a file in a search path

FaceBoxes/utils/build.py:18

Methodfinish

(self)

utils/progress/progress/helpers.py:71

Functionflip

flip a face and its landmark

common/utils.py:114

Methodforward

(self, x)

FaceBoxes/models/faceboxes.py:15

Methodforward

(self, x)

FaceBoxes/models/faceboxes.py:32

Methodforward

(self, x)

FaceBoxes/models/faceboxes.py:56

Methodforward

(self, x)

FaceBoxes/models/faceboxes.py:113

Methodforward

Multibox Loss Args: predictions (tuple): A tuple containing loc preds, conf preds, and prior boxes from SSD net.

Retinaface/layers/modules/multibox_loss.py:44

Methodforward

(self, input)

Retinaface/models/net.py:55

Methodforward

(self, input)

Retinaface/models/net.py:81

Methodforward

(self, x)

Retinaface/models/net.py:128

Methodforward

(self,x)

Retinaface/models/retinaface.py:20

Methodforward

(self,x)

Retinaface/models/retinaface.py:31

Methodforward

(self,x)

Retinaface/models/retinaface.py:42

Methodforward

(self,inputs)

Retinaface/models/retinaface.py:107

Methodforward

Arguments: x: a float tensor with shape [batch_size, c, h, w]. Returns: a float tensor with shape [batch_size

MTCNN/get_nets.py:13

Methodforward

Arguments: x: a float tensor with shape [batch_size, 3, h, w]. Returns: b: a float tensor with shape [batch_s

MTCNN/get_nets.py:59

Methodforward

Arguments: x: a float tensor with shape [batch_size, 3, h, w]. Returns: b: a float tensor with shape [batch_s

MTCNN/get_nets.py:105

Methodforward

Arguments: x: a float tensor with shape [batch_size, 3, h, w]. Returns: c: a float tensor with shape [batch_s

MTCNN/get_nets.py:156

Methodforward

(self, x)

vision/nn/mb_tiny_RFB.py:20

Methodforward

(self, x)

vision/nn/mb_tiny_RFB.py:58

Methodforward

(self, x)

vision/nn/mb_tiny_RFB.py:113

Methodforward

(self, x)

vision/nn/mb_tiny.py:46

Methodforward

Compute classification loss and smooth l1 loss. Args: confidence (batch_size, num_priors, num_classes): class predictions.

vision/nn/multibox_loss.py:24

Methodforward

(self, x)

models/pfld_compressed.py:54

Methodforward

(self, x)

models/pfld_compressed.py:117

models/mobilefacenet.py:12

Methodforward

(self, x)

models/mobilefacenet.py:23

← previous next →201–300 of 362, ranked by callers