Functions — github.com/Sin3DM/Sin3DM

CodeHub MCPcopy Create free account

hub / github.com/Sin3DM/Sin3DM / functions

Functions339 in github.com/Sin3DM/Sin3DM

⨍ Functions 339◇ Types & classes 50

Functionget_named_beta_schedule

Get a pre-defined beta schedule for the given name. The beta schedule library consists of beta schedules which remain similar in the lim

src/diffusion/gaussian_diffusion.py:19

src/diffusion/logger.py:243

src/diffusion/logger.py:258

src/diffusion/gaussian_diffusion.py:98

Methodlatent_dim

src/encoding/blocks.py:21

Functionload_state_dict

Load a PyTorch file without redundant fetches across MPI ranks.

src/utils/dist_util.py:55

Functionlogkv_mean

The same as logkv(), but if called many times, values averaged.

src/diffusion/logger.py:221

Log a dictionary of key-value pairs

src/diffusion/logger.py:228

( example, n_samples=4, rand_seed=0, mc_reso=256, n_faces=10000, tex_reso=2048, re

Methodp_mean_variance

( self, model, *args, **kwargs )

src/diffusion/respace.py:88

Functionpad_composed_featmaps

(composed_map, sizes, pad_sizes)

src/utils/triplane_util.py:28

Methodprocess_xstart

src/diffusion/gaussian_diffusion.py:294

Functionprofile

Usage: @profile("my_func") def my_func(): code

src/diffusion/logger.py:303

src/diffusion/logger.py:479

Methodreset_aabb

src/encoding/networks.py:157

Methodreset_aabb

src/encoding/networks.py:264

Methodsave_checkpoint

src/diffusion/train_util.py:259

Functionscale_module

Scale the parameters of a module and return it.

src/diffusion/nn.py:77

Functionscoped_configure

(dir=None, format_strs=None, comm=None)

src/diffusion/logger.py:487

Functionset_comm

src/diffusion/logger.py:277

Functionset_level

Set logging threshold on current logger.

src/diffusion/logger.py:270

Functionsetup_dist

Setup a distributed process group.

src/utils/dist_util.py:19

Functionstr2bool

https://stackoverflow.com/questions/15008758/parsing-boolean-values-with-argparse

src/utils/parser_util.py:203

Methodsummary_val

src/diffusion/logger.py:172

Functionsync_params

Synchronize a sequence of Tensors across ranks from rank 0.

src/utils/dist_util.py:62

Methodtex_parameters

src/encoding/networks.py:154

Methodtex_parameters

src/encoding/networks.py:260

Methodtraining_losses

Compute training losses for a single timestep. :param model: the model to evaluate loss on. :param x_start: the [N x C x ...

src/diffusion/gaussian_diffusion.py:771

Methodtraining_losses

( self, model, *args, **kwargs )

src/diffusion/respace.py:93

Functiontree_postprocessor

src/encoding/utils3d.py:126

Methodupdate_with_all_losses

(self, ts, losses)

src/diffusion/resample.py:143

src/diffusion/logger.py:262

src/diffusion/resample.py:66

src/diffusion/resample.py:134

src/diffusion/logger.py:48

src/diffusion/logger.py:102

src/diffusion/logger.py:119

src/diffusion/logger.py:171

src/diffusion/logger.py:84

← previous301–339 of 339, ranked by callers