MCPcopy Create free account

hub / github.com/Kevinfringe/MegaPortrait / functions

Functions46 in github.com/Kevinfringe/MegaPortrait

↓ 11 callersMethod__init__
(self, input_channels)
model.py:393
↓ 4 callersFunctioncosine_distance
(args, z1, z2)
train.py:34
↓ 2 callersFunctioncapture_frames
:param n: :param path: :param flag: if flag = 1, then it generate source img, otherwise, generate driver img. :return:
data_generator.py:27
↓ 1 callersMethod__init__
VGGFace model. Face recognition network. It takes as input a Bx3x224x224 batch of face images and gives as output a BxC score vector
vgg_face.py:33
↓ 1 callersFunctioncosine_loss
( args, descriptor_driver, descriptor_source_rand, descriptor_driver_rand)
train.py:43
↓ 1 callersFunctionmain
()
train.py:206
↓ 1 callersFunctiontensor2image
(image, norm=255.0)
test.py:22
↓ 1 callersFunctiontrain
(args, models, device, driver_loader, source_loader, optimizers, schedulers, source_img_random, driver_img_ran
train.py:69
Method__getitem__
(self, item)
dataset.py:17
Method__getitem__
(self, item)
dataset.py:37
Method__init__
(self, in_channels=3)
patchGAN.py:9
Method__init__
(self, source_img_path, length, transform=None)
dataset.py:9
Method__init__
(self, driver_img_path, length, transform=None)
dataset.py:29
Method__init__
Create a block with len(units) - 1 convolutions. convolution number i transforms the number of channels from units[i - 1] to units[i]
vgg_face.py:74
Method__init__
(self, in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bia
model.py:10
Method__init__
(self, in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bia
model.py:26
Method__init__
(self, dimension, input_channels, output_channels)
model.py:45
Method__init__
(self)
model.py:87
Method__init__
(self, repeat, in_channels=3, outputs=256)
model.py:156
Method__init__
(self, in_channels, out_channels, downsample=False)
model.py:207
Method__init__
(self, in_channels, resblock=ResBlock, outputs=256)
model.py:233
Method__init__
(self, in_channels, resblock, outputs=256)
model.py:281
Method__init__
(self, input_channels, output_channels)
model.py:329
Method__init__
(self, input_channels)
model.py:357
Method__init__
(self, input_channels)
model.py:427
Method__len__
(self)
dataset.py:14
Method__len__
(self)
dataset.py:34
Methoddiscriminator_block
Returns downsampling layers of each discriminator block
patchGAN.py:12
Functionface_detect
(img)
data_generator.py:14
Methodforward
(self, img_A, img_B)
patchGAN.py:29
Methodforward
(self, x)
vgg_face.py:58
Methodforward
(self, x)
vgg_face.py:87
Methodforward
(self, x)
model.py:15
Methodforward
(self, x)
model.py:31
Methodforward
(self, x)
model.py:66
Methodforward
(self, x)
model.py:101
Methodforward
(self, input)
model.py:191
Methodforward
(self, input)
model.py:223
Methodforward
(self, input)
model.py:265
Methodforward
(self, input)
model.py:313
Methodforward
(self, x)
model.py:341
Methodforward
(self, x)
model.py:372
Methodforward
(self, x)
model.py:397
Methodforward
(self, x)
model.py:451
Functionhead_pose_estimation
(imgs, source=True)
HeadPoseEstimation.py:149
Functionvggface
VGGFace model. Args: pretrained (bool): If True, returns pre-trained model
vgg_face.py:19