MCPcopy Create free account

hub / github.com/autonomousvision/stylegan-xl / functions

Functions736 in github.com/autonomousvision/stylegan-xl

⨍ Functions 736◇ Types & classes 120↳ Endpoints 8
↓ 1 callersMethod_tweak_network
(self, net)
viz/renderer.py:184
↓ 1 callersFunction_upfirdn2d_ref
Slow reference implementation of `upfirdn2d()` using standard PyTorch ops.
torch_utils/ops/upfirdn2d.py:167
↓ 1 callersMethodaccumulate_gradients
(self, phase, real_img, real_c, gen_z, gen_c, gain, cur_nimg)
training/loss.py:32
↓ 1 callersMethodadd_recent
(self, pkl, ignore_errors=False)
viz/pickle_widget.py:38
↓ 1 callersFunctionapply_affine_transformation
(x, mat, up=4, **filter_kwargs)
metrics/equivariance.py:135
↓ 1 callersFunctionapply_fractional_pseudo_rotation
(x, angle, a=3, **filter_kwargs)
metrics/equivariance.py:179
↓ 1 callersFunctionapply_fractional_rotation
(x, angle, a=3, **filter_kwargs)
metrics/equivariance.py:169
↓ 1 callersFunctionapply_fractional_translation
(x, tx, ty, a=3)
metrics/equivariance.py:63
↓ 1 callersFunctionapply_integer_translation
(x, tx, ty)
metrics/equivariance.py:44
↓ 1 callersMethodas_dict
r"""Returns the averages accumulated between the last two calls to `update()` as an `dnnlib.EasyDict`. The contents are as follows:
torch_utils/training_stats.py:212
↓ 1 callersMethodattention
(self, x: torch.Tensor)
feature_networks/clip/model.py:181
↓ 1 callersFunctionavailable_models
Returns the names of available CLIP models
feature_networks/clip/clip.py:69
↓ 1 callersFunctionazimuthal_average
Calculate the azimuthally averaged radial profile. Requires low frequencies to be at the center of the image. Args: image: Batch
torch_utils/utils_spectrum.py:57
↓ 1 callersFunctionbasic_clean
(text)
feature_networks/clip/simple_tokenizer.py:50
↓ 1 callersFunctionbatch_fft
Compute fourier transform of batch. Args: data: input tensor, (NxHxW) Returns: Batch fourier transform of input data.
torch_utils/utils_spectrum.py:30
↓ 1 callersMethodbpe
(self, token)
feature_networks/clip/simple_tokenizer.py:80
↓ 1 callersMethodbuild_attention_mask
(self)
feature_networks/clip/model.py:324
↓ 1 callersFunctionbuild_model
(state_dict: dict)
feature_networks/clip/model.py:416
↓ 1 callersFunctioncalc_dims
(pretrained, is_vit=False)
feature_networks/pretrained_builder.py:171
↓ 1 callersFunctioncalc_metrics
Calculate quality metrics for previous training run or pretrained network pickle. Examples: \b # Previous training run: look up options
calc_metrics.py:98
↓ 1 callersFunctioncall_func_by_name
Finds the python object with the given name and calls it as a function.
dnnlib/util.py:293
↓ 1 callersMethodcapture_next_frame
(self)
gui_utils/glfw_window.py:139
↓ 1 callersMethodclose
(self)
visualizer.py:68
↓ 1 callersMethodclose
(self)
gui_utils/glfw_window.py:45
↓ 1 callersMethodcompute_superres_filterparams
(self, up_factor, img_resolution, last_stem_layer, head_layers, num_critical=2)
training/networks_stylegan3_resetting.py:697
↓ 1 callersFunctionconvTranspose2d
(*args, **kwargs)
pg_modules/blocks.py:14
↓ 1 callersFunctionconvert_dataset
Convert an image dataset into a dataset archive usable with StyleGAN2 ADA PyTorch. The input dataset format is guessed from the --source argument
dataset_tool.py:343
↓ 1 callersFunctionconvert_network_pickle
Convert legacy network pickle into the native PyTorch format. The tool is able to load the main network configurations exported using the TensorF
legacy.py:303
↓ 1 callersFunctionconvert_tf_discriminator
(tf_D)
legacy.py:214
↓ 1 callersFunctiondefault_bpe
()
feature_networks/clip/simple_tokenizer.py:11
↓ 1 callersMethoddelete
(self)
gui_utils/gl_utils.py:161
↓ 1 callersMethoddelete
(self)
gui_utils/gl_utils.py:272
↓ 1 callersMethoddisplay
(self, batch)
run_stylemc.py:56
↓ 1 callersMethoddraw_frame
(self)
visualizer.py:106
↓ 1 callersFunctiondraw_rect
(*, pos=0, pos2=None, size=None, align=0, rint=False, color=1, alpha=1, rounding=0)
gui_utils/gl_utils.py:335
↓ 1 callersFunctionembed_text
(model, prompt, device='cuda')
run_stylemc.py:130
↓ 1 callersMethodencode_image
(self, image)
feature_networks/clip/model.py:336
↓ 1 callersFunctionfind_direction
( G, styles, text_prompt, layers, seeds, class_idx=None, batch_size=8, device=
run_stylemc.py:176
↓ 1 callersMethodforward
(self, image, text)
feature_networks/clip/model.py:359
↓ 1 callersFunctiongen_interp_video
(G, mp4: str, seeds, shuffle_seed=None, w_frames=60*4, kind='cubic', grid_dims=(1,1), num_keyframes=None, wrap
gen_video.py:47
↓ 1 callersFunctiongenerate_edit
( G, styles, direction, edit_strength, path, save_video=True, device='cuda', )
run_stylemc.py:137
↓ 1 callersFunctiongenerate_images
Render a latent vector interpolation video. Examples: \b # Render a 4x2 grid of interpolations for seeds 0 through 31. python gen_vi
gen_video.py:151
↓ 1 callersFunctiongenerate_images
( network_pkl: str, seeds: List[int], batch_sz: int, truncation_psi: float, centroids_path
gen_images.py:83
↓ 1 callersFunctiongenerate_samplesheet
( network_pkl: str, truncation_psi: float, seed: int, centroids_path: str, classes: List[i
gen_class_samplesheet.py:27
↓ 1 callersFunctionget_array
(string, *, dropshadow_radius: int=None, **kwargs)
gui_utils/text_utils.py:36
↓ 1 callersFunctionget_children
(model: torch.nn.Module)
torch_utils/misc.py:154
↓ 1 callersFunctionget_default_font
()
gui_utils/text_utils.py:22
↓ 1 callersMethodget_details
(self, idx)
training/dataset.py:119
↓ 1 callersFunctionget_feature_detector_name
(url)
metrics/metric_utils.py:52
↓ 1 callersMethodget_layer_specs
(self)
training/networks_stylegan3_resetting.py:523
↓ 1 callersFunctionget_morphed_w_code
(new_w_code, fixed_w, regularizer_alpha=30)
run_inversion.py:25
↓ 1 callersMethodget_network
(self, pkl, key, **tweak_kwargs)
viz/renderer.py:152
↓ 1 callersFunctionget_obj_by_name
Finds the python object with the given name.
dnnlib/util.py:287
↓ 1 callersMethodget_result
(self)
visualizer.py:232
↓ 1 callersFunctionget_w_from_file
(file, device='cuda', return_ext=False)
torch_utils/gen_utils.py:471
↓ 1 callersFunctionhook
(model, input, output)
metrics/metric_utils.py:212
↓ 1 callersFunctioninit_dataset_kwargs
(data)
train.py:110
↓ 1 callersMethodinit_upfirdn
(self, in_sampling_rate, out_sampling_rate, in_cutoff, out_cutoff, in_half_width, out_hal
training/networks_stylegan3_resetting.py:348
↓ 1 callersMethodinitialize_parameters
(self)
feature_networks/clip/model.py:295
↓ 1 callersMethodis_full
(self)
metrics/metric_utils.py:105
↓ 1 callersMethodis_skipping_frames
(self)
gui_utils/glfw_window.py:136
↓ 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:312
↓ 1 callersFunctionis_url
Determine whether the given object is a valid URL string.
dnnlib/util.py:378
↓ 1 callersFunctionitem_width
(width=None)
gui_utils/imgui_utils.py:70
↓ 1 callersFunctionlaunch_training
(c, desc, outdir, dry_run)
train.py:53
↓ 1 callersFunctionlayout_grid
(img, grid_w=None, grid_h=1, float_to_uint8=True, chw_to_hwc=True, to_numpy=True)
gen_video.py:29
↓ 1 callersFunctionlerp
Linear interpolation between v0 (starting) and v1 (final) vectors; for optimal results, use t as an np.ndarray to return all results at once
torch_utils/gen_utils.py:175
↓ 1 callersMethodlist_runs_and_pkls
(self, parents)
viz/pickle_widget.py:133
↓ 1 callersFunctionload
Load a CLIP model Parameters ---------- name : str A model name listed by `clip.available_models()`, or the path to a model check
feature_networks/clip/clip.py:74
↓ 1 callersFunctionload_network_pkl
(f, force_fp16=False)
legacy.py:24
↓ 1 callersMethodload_pickle
(self, pkl, ignore_errors=False)
visualizer.py:77
↓ 1 callersFunctionmain
(**kwargs)
train.py:177
↓ 1 callersFunctionmain
Interactive model visualizer. Optional PATH argument can be used specify which .pkl file to load.
visualizer.py:270
↓ 1 callersFunctionmake_cache_dir_path
(*paths: str)
dnnlib/util.py:124
↓ 1 callersFunctionmake_transform
( transform: Optional[str], output_width: Optional[int], output_height: Optional[int] )
dataset_tool.py:232
↓ 1 callersFunctionmake_transform
(translate: Tuple[float,float], angle: float)
gen_images.py:58
↓ 1 callersMethodmaximize
(self)
gui_utils/glfw_window.py:109
↓ 1 callersFunctionmodulated_conv2d
( x, # Input tensor: [batch_size, in_channels, in_height, in_width] w,
training/networks_stylegan3.py:29
↓ 1 callersFunctionmodulated_conv2d
( x, # Input tensor: [batch_size, in_channels, in_height, in_width] w,
training/networks_stylegan3_resetting.py:32
↓ 1 callersFunctionnan_to_num
(input, nan=0.0, posinf=None, neginf=None, *, out=None)
torch_utils/misc.py:49
↓ 1 callersMethodnum
r"""Returns the number of scalars that were accumulated for the given statistic between the last two calls to `update()`, or zero if n
torch_utils/training_stats.py:180
↓ 1 callersFunctionopen_cifar10
(tarball: str, *, max_images: Optional[int])
dataset_tool.py:170
↓ 1 callersFunctionopen_dataset
(source, *, max_images: Optional[int])
dataset_tool.py:284
↓ 1 callersFunctionopen_dest
(dest: str)
dataset_tool.py:304
↓ 1 callersFunctionopen_image_folder
(source_dir, *, max_images: Optional[int])
dataset_tool.py:79
↓ 1 callersFunctionopen_image_zip
(source, *, max_images: Optional[int])
dataset_tool.py:113
↓ 1 callersFunctionopen_lmdb
(lmdb_dir: str, *, max_images: Optional[int])
dataset_tool.py:142
↓ 1 callersFunctionopen_mnist
(images_gz: str, *, max_images: Optional[int])
dataset_tool.py:202
↓ 1 callersFunctionpersistent_class
r"""Class decorator that extends a given class to save its source code when pickled. Example: from torch_utils import persistence
torch_utils/persistence.py:35
↓ 1 callersFunctionpivotal_tuning
( G, w_pivot, target, device: torch.device, num_steps=350, learning_rate = 3e-4, n
run_inversion.py:71
↓ 1 callersFunctionpng_to_rgb
(arr)
dataset_tool.py:68
↓ 1 callersMethodpop_captured_frame
(self)
gui_utils/glfw_window.py:142
↓ 1 callersMethodpop_drag_and_drop_paths
(self)
gui_utils/glfw_window.py:147
↓ 1 callersMethodprint_error
(self, error)
visualizer.py:80
↓ 1 callersFunctionproject
( G, target: torch.Tensor, # [C,H,W] and dynamic range [0,255], W & H must match G output resolution
run_inversion.py:142
↓ 1 callersFunctionprompts_dist_loss
(x, targets, loss)
run_stylemc.py:123
↓ 1 callersFunctionrecurse
(obj)
torch_utils/persistence.py:236
↓ 1 callersFunctionreport
r"""Broadcasts the given set of scalars to all interested instances of `Collector`, across device and process boundaries. This function is ex
torch_utils/training_stats.py:56
↓ 1 callersMethodreset
(self)
run_stylemc.py:33
↓ 1 callersFunctionroll_quadrants
Shift low frequencies to the center of fourier transform, i.e. [-N/2, ..., +N/2] -> [0, ..., N-1] Args: data: fourier transform, (NxH
torch_utils/utils_spectrum.py:5
← previousnext →201–300 of 736, ranked by callers