Functions — github.com/AlexiaJM/MaximumMarginGANs

CodeHub MCPcopy Create free account

hub / github.com/AlexiaJM/MaximumMarginGANs / functions

Functions52 in github.com/AlexiaJM/MaximumMarginGANs

⨍ Functions 52 ◇ Types & classes 10

↓ 10 callersMethod__init__

Code/GAN.py:283

↓ 2 callersFunction_get_inception_layer

Prepares inception net for batched usage and returns pool_3 layer.

Code/fid_new.py:46

↓ 2 callersFunction_handle_path

(path, sess, low_profile=False)

Code/fid_new.py:278

↓ 2 callersFunction_handle_path

Code/fid.py:208

↓ 2 callersFunctionregister_creator

In the forward pass, our Function.__call__ and BatchNorm.forward_hook both call this method to register the creators inputs: list of input

Code/pytorch_visualize.py:32

↓ 2 callersFunctionsize_to_str

Code/pytorch_visualize.py:154

↓ 2 callersFunctionsizestr

Code/pytorch_visualize.py:101

↓ 1 callersFunction_get_inception_layer

Prepares inception net for batched usage and returns pool_3 layer.

↓ 1 callersFunctionadd_nodes

Code/pytorch_visualize.py:157

↓ 1 callersFunctioncalculate_activation_statistics

Calculation of the statistics used by the FID. Params: -- images : Numpy array of dimension (n_images, hi, wi, 3). The values

Code/fid_new.py:159

↓ 1 callersFunctioncalculate_activation_statistics

Calculation of the statistics used by the FID. Params: -- images : Numpy array of dimension (n_images, hi, wi, 3). The values

Code/fid.py:162

↓ 1 callersFunctioncalculate_activation_statistics_from_files

Calculation of the statistics used by the FID. Params: -- files : list of paths to image files. Images need to have same dimensions for a

Code/fid_new.py:232

↓ 1 callersFunctioncalculate_fid_given_paths

Calculates the FID of two paths.

Code/fid_new.py:295

↓ 1 callersFunctioncalculate_fid_given_paths

Calculates the FID of two paths.

Code/fid.py:221

↓ 1 callersFunctioncalculate_frechet_distance

Numpy implementation of the Frechet Distance. The Frechet distance between two multivariate Gaussians X_1 ~ N(mu_1, C_1) and X_2 ~ N(mu_2, C_2

Code/fid_new.py:104

↓ 1 callersFunctioncalculate_frechet_distance

Numpy implementation of the Frechet Distance. The Frechet distance between two multivariate Gaussians X_1 ~ N(mu_1, C_1) and X_2 ~ N(mu_2, C_2

Code/fid.py:107

↓ 1 callersFunctioncheck_or_download_inception

Checks if the path to the inception file is valid, or downloads the file if it is not present.

Code/fid_new.py:260

↓ 1 callersFunctioncheck_or_download_inception

Checks if the path to the inception file is valid, or downloads the file if it is not present.

Code/fid.py:190

↓ 1 callersFunctioncreate_inception_graph

Creates a graph from saved GraphDef file.

Code/fid_new.py:34

↓ 1 callersFunctioncreate_inception_graph

Creates a graph from saved GraphDef file.

↓ 1 callersFunctiondescribePositive

Code/preprocess_cat_dataset.py:82

↓ 1 callersFunctiongenerate_random_sample

(size=param.batch_size)

Code/GAN.py:253

↓ 1 callersFunctionget_activations

Calculates the activations of the pool_3 layer for all images. Params: -- images : Numpy array of dimension (n_images, hi, wi, 3). The v

Code/fid_new.py:67

↓ 1 callersFunctionget_activations

Calculates the activations of the pool_3 layer for all images. Params: -- images : Numpy array of dimension (n_images, hi, wi, 3). The v

↓ 1 callersFunctionget_activations_from_files

Calculates the activations of the pool_3 layer for all images. Params: -- files : list of paths to image files. Images need to have same

Code/fid_new.py:197

↓ 1 callersFunctionload_image_batch

Convenience method for batch-loading images Params: -- files : list of paths to image files. Images need to have same dimensions for all fi

Code/fid_new.py:188

↓ 1 callersFunctionmain

Code/preprocess_cat_dataset.py:125

↓ 1 callersFunctionpreprocessCatFace

(coords, image)

Code/preprocess_cat_dataset.py:29

↓ 1 callersFunctionremove_vis_hooks

Code/pytorch_visualize.py:92

↓ 1 callersFunctionrotateCoords

(coords, center, angleRadians)

Code/preprocess_cat_dataset.py:9

Code/GAN.py:264

Code/GAN.py:332

(self, n_input, n_output, k_size)

Code/GAN.py:557

(self, n_input, n_output, k_size)

Code/GAN.py:567

(self, n_input, n_output, k_size)

Code/GAN.py:577

(self, n_input, n_output, k_size, resample='up', bn=True, spatial_dim=None)

Code/GAN.py:590

(self, n_output)

Code/GAN.py:629

Code/GAN.py:267

Code/GAN.py:323

Code/GAN.py:405

Code/GAN.py:561

Code/GAN.py:571

Code/GAN.py:584

Code/GAN.py:622

Code/GAN.py:642

Functionhook_func

(module, inputs, output)

Code/pytorch_visualize.py:69

Functionmake_dot

Produces Graphviz representation of PyTorch autograd graph Blue nodes are the Variables that require grad, orange are Tensors saved f

Code/pytorch_visualize.py:131

Functionnew_function__call__

(self, *args, **kwargs)

Code/pytorch_visualize.py:82

Functionregister_vis_hooks

Code/pytorch_visualize.py:60

Functionsave_visualization

(name, format='svg')

Code/pytorch_visualize.py:99

FunctionstrToBool

Functionweights_init

Code/GAN.py:697