MCPcopy Create free account

hub / github.com/NVlabs/stylegan / functions

Functions280 in github.com/NVlabs/stylegan

⨍ Functions 280◇ Types & classes 20
↓ 1 callersFunction_handle_legacy_output_transforms
(output_transform, dynamic_kwargs)
dnnlib/tflib/network.py:556
↓ 1 callersMethod_iterate_reals
(self, minibatch_size)
metrics/metric_base.py:101
↓ 1 callersFunction_populate_run_dir
Copy all necessary files into the run dir. Assumes that the dir exists, is local, and is writable.
dnnlib/submission/submit.py:196
↓ 1 callersMethodadd_task
(self, func, args=())
dataset_tool.py:142
↓ 1 callersFunctionadjust_dynamic_range
(data, drange_in, drange_out)
training/misc.py:42
↓ 1 callersFunctionapply_noise
(x, noise_var=None, randomize_noise=True)
training/networks_stylegan.py:270
↓ 1 callersMethodclose
(self)
dataset_tool.py:51
↓ 1 callersFunctionconditional_entropy
(p)
metrics/linear_separability.py:95
↓ 1 callersFunctionconv2d_downscale2d
(x, fmaps, kernel, gain=np.sqrt(2), use_wscale=False)
training/networks_progan.py:113
↓ 1 callersFunctionconv2d_downscale2d
(x, fmaps, kernel, fused_scale='auto', **kwargs)
training/networks_stylegan.py:193
↓ 1 callersFunctioncreate_image_grid
(images, grid_size=None)
training/misc.py:49
↓ 1 callersFunctioncreate_session
Create tf.Session based on config dict.
dnnlib/tflib/tfutil.py:128
↓ 1 callersFunctiondraw_noise_components_figure
(png, Gs, w, h, seeds, noise_ranges, flips)
generate_figures.py:103
↓ 1 callersFunctiondraw_noise_detail_figure
(png, Gs, w, h, num_samples, seeds)
generate_figures.py:83
↓ 1 callersFunctiondraw_style_mixing_figure
(png, Gs, w, h, src_seeds, dst_seeds, style_ranges)
generate_figures.py:59
↓ 1 callersFunctiondraw_truncation_trick_figure
(png, Gs, w, h, seeds, psis)
generate_figures.py:127
↓ 1 callersFunctionentropy
(p)
metrics/linear_separability.py:85
↓ 1 callersFunctionexecute_cmdline
(argv)
dataset_tool.py:546
↓ 1 callersFunctionfinalize_autosummaries
Create the necessary ops to include autosummaries in TensorBoard report. Note: This should be done only once per graph.
dnnlib/tflib/autosummary.py:112
↓ 1 callersMethodfinish
(self)
dataset_tool.py:155
↓ 1 callersMethodget_minibatch_tf
(self)
training/dataset.py:195
↓ 1 callersFunctionget_obj_by_name
Finds the python object with the given name.
dnnlib/util.py:246
↓ 1 callersMethodget_random_labels_tf
(self, minibatch_size)
training/dataset.py:209
↓ 1 callersMethodget_result
(self, func)
dataset_tool.py:148
↓ 1 callersFunctionget_template_from_path
Convert a normal path back to its template representation.
dnnlib/submission/submit.py:123
↓ 1 callersMethodget_time_since_last_update
How much time has passed since the last call to update.
dnnlib/submission/run_context.py:82
↓ 1 callersMethodget_time_since_start
How much time has passed since the creation of the context.
dnnlib/submission/run_context.py:78
↓ 1 callersMethodget_var
Get the value of a given variable as NumPy array. Note: This method is very inefficient -- prefer to use tflib.run(list_of_vars) whenever poss
dnnlib/tflib/network.py:246
↓ 1 callersFunctioninstance_norm
(x, epsilon=1e-8)
training/networks_stylegan.py:247
↓ 1 callersFunctionis_top_level_function
Determine whether the given object is a top-level function, i.e., defined at module scope using 'def'.
dnnlib/util.py:266
↓ 1 callersFunctionis_url
Determine whether the given object is a valid URL string.
dnnlib/util.py:329
↓ 1 callersMethodlist_layers
Returns a list of (layer_name, output_expr, trainable_vars) tuples corresponding to individual layers of the network. Mainly intended to be us
dnnlib/tflib/network.py:464
↓ 1 callersFunctionlist_network_pkls
(run_id_or_run_dir, include_final=True)
training/misc.py:113
↓ 1 callersMethodlist_ops
(self)
dnnlib/tflib/network.py:456
↓ 1 callersFunctionload_pkl
(file_or_url)
training/misc.py:31
↓ 1 callersFunctionlocate_network_pkl
(run_id_or_run_dir_or_network_pkl, snapshot_or_network_pkl=None)
training/misc.py:122
↓ 1 callersFunctionmain
()
train.py:177
↓ 1 callersFunctionmain
()
generate_figures.py:144
↓ 1 callersFunctionmain
()
run_metrics.py:62
↓ 1 callersFunctionmain
()
pretrained_example.py:18
↓ 1 callersFunctionmain
()
dnnlib/submission/_internal/run.py:22
↓ 1 callersFunctionminibatch_stddev_layer
(x, group_size=4, num_new_features=1)
training/networks_progan.py:131
↓ 1 callersFunctionminibatch_stddev_layer
(x, group_size=4, num_new_features=1)
training/networks_stylegan.py:283
↓ 1 callersFunctionmutual_information
(p)
metrics/linear_separability.py:71
↓ 1 callersFunctionopen_file_or_url
(file_or_url)
training/misc.py:26
↓ 1 callersFunctionparse_config_for_previous_run
(run_id)
training/misc.py:155
↓ 1 callersFunctionparse_tfrecord_np
(record)
training/dataset.py:27
↓ 1 callersFunctionprocess_reals
(x, lod, mirror_augment, drange_data, drange_net)
training/training_loop.py:26
↓ 1 callersMethodrun
(self, *args, **kwargs)
metrics/metric_base.py:123
↓ 1 callersFunctionrun_wrapper
Wrap the actual run function call for handling logging, exceptions, typing, etc.
dnnlib/submission/submit.py:224
↓ 1 callersFunctionset_vars
Set the values of given tf.Variables. Equivalent to the following, but more efficient and does not bloat the tf graph: tflib.run([tf.assign(v
dnnlib/tflib/tfutil.py:182
↓ 1 callersMethodsetup_as_moving_average_of
Construct a TensorFlow op that updates the variables of this network to be slightly closer to those of the given network.
dnnlib/tflib/network.py:342
↓ 1 callersMethodshould_stop
Tell whether a stopping condition has been triggered one way or another.
dnnlib/submission/run_context.py:74
↓ 1 callersFunctionstyle_mod
(x, dlatent, **kwargs)
training/networks_stylegan.py:261
↓ 1 callersMethodupdate_autosummaries
(self)
metrics/metric_base.py:83
↓ 1 callersMethodupdate_autosummaries
(self)
metrics/metric_base.py:130
↓ 1 callersFunctionupscale2d_conv2d
(x, fmaps, kernel, gain=np.sqrt(2), use_wscale=False)
training/networks_progan.py:89
↓ 1 callersFunctionupscale2d_conv2d
(x, fmaps, kernel, fused_scale='auto', **kwargs)
training/networks_stylegan.py:174
FunctionD_basic
( images_in, # First input: Images [minibatch, channel, height, width]. label
training/networks_stylegan.py:564
FunctionD_hinge
(G, D, opt, training_set, minibatch_size, reals, labels)
training/loss.py:83
FunctionD_hinge_gp
(G, D, opt, training_set, minibatch_size, reals, labels, # pylint: disable=unused-argument wgan_lambda
training/loss.py:93
FunctionD_logistic
(G, D, opt, training_set, minibatch_size, reals, labels)
training/loss.py:139
FunctionD_logistic_simplegp
(G, D, opt, training_set, minibatch_size, reals, labels, r1_gamma=10.0, r2_gamma=0.0)
training/loss.py:150
FunctionD_paper
( images_in, # First input: Images [minibatch, channel, height, width]. label
training/networks_progan.py:238
FunctionD_wgan
(G, D, opt, training_set, minibatch_size, reals, labels, # pylint: disable=unused-argument wgan_epsilon =
training/loss.py:34
FunctionD_wgan_gp
(G, D, opt, training_set, minibatch_size, reals, labels, # pylint: disable=unused-argument wgan_lambda
training/loss.py:50
FunctionG_logistic_nonsaturating
(G, D, opt, training_set, minibatch_size)
training/loss.py:131
FunctionG_logistic_saturating
(G, D, opt, training_set, minibatch_size)
training/loss.py:123
FunctionG_mapping
( latents_in, # First input: Latent vectors (Z) [minibatch, latent_size].
training/networks_stylegan.py:384
FunctionG_paper
( latents_in, # First input: Latent vectors [minibatch, latent_size]. labels_i
training/networks_progan.py:149
FunctionG_style
( latents_in, # First input: Latent vectors (Z) [minibatch, latent_siz
training/networks_stylegan.py:302
FunctionG_synthesis
( dlatents_in, # Input: Disentangled latents (W) [minibatch, num_layers, dlatent_si
training/networks_stylegan.py:440
FunctionG_wgan
(G, D, opt, training_set, minibatch_size)
training/loss.py:26
Method__delattr__
(self, name: str)
dnnlib/util.py:48
Method__enter__
(self)
dataset_tool.py:98
Method__enter__
(self)
dataset_tool.py:159
Method__enter__
(self)
dnnlib/util.py:68
Method__exit__
(self, *args)
dataset_tool.py:101
Method__exit__
(self, *excinfo)
dataset_tool.py:162
Method__exit__
(self, exc_type: Any, exc_value: Any, traceback: Any)
dnnlib/util.py:71
Method__exit__
(self, exc_type: Any, exc_value: Any, traceback: Any)
dnnlib/submission/run_context.py:58
Method__getattr__
(self, name: str)
dnnlib/util.py:39
Method__getstate__
Pickle export.
dnnlib/tflib/network.py:256
Method__init__
(self, tfrecord_dir, expected_images, print_progress=True, progress_interval=10)
dataset_tool.py:34
Method__init__
(self)
dataset_tool.py:107
Method__init__
(self, task_queue)
dataset_tool.py:114
Method__init__
(self, name)
metrics/metric_base.py:37
Method__init__
(self, metric_kwarg_list)
metrics/metric_base.py:120
Method__init__
(self, num_samples, epsilon, space, sampling, minibatch_per_gpu, **kwargs)
metrics/perceptual_path_length.py:36
Method__init__
(self, num_samples, num_keep, attrib_indices, minibatch_per_gpu, **kwargs)
metrics/linear_separability.py:105
Method__init__
(self, num_images, minibatch_per_gpu, **kwargs)
metrics/frechet_inception_distance.py:22
Method__init__
(self, tfrecord_dir, # Directory containing a collection of tfrecords files. res
training/dataset.py:38
Method__init__
(self, resolution=1024, num_channels=3, dtype='uint8', dynamic_range=[0,255], label_size=0, label_dtype='float
training/dataset.py:172
Method__init__
(self, file_name: str = None, file_mode: str = "w", should_flush: bool = True)
dnnlib/util.py:55
Method__init__
(self, name: str = None, func_name: Any = None, **static_kwargs)
dnnlib/tflib/network.py:74
Method__init__
(self, name: str = "Train", tf_optimizer: str = "tf.train.AdamOptimizer",
dnnlib/tflib/optimizer.py:40
Method__init__
(self, submit_config: submit.SubmitConfig, config_module: types.ModuleType = None, max_epoch: Any = None)
dnnlib/submission/run_context.py:35
Method__init__
(self)
dnnlib/submission/submit.py:75
Method__setattr__
(self, name: str, value: Any)
dnnlib/util.py:45
Method__setstate__
Pickle import.
dnnlib/tflib/network.py:268
← previousnext →101–200 of 280, ranked by callers