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

↓ 1 callersFunctiontrain_diffusion

src/train.py:33

↓ 1 callersFunctionupdate_ema

Update target parameters to be closer to those of source parameters using an exponential moving average. :param target_params: the targe

src/diffusion/nn.py:55

↓ 1 callersMethodupdate_network

update network by back propagation

src/encoding/model.py:178

↓ 1 callersMethodupdate_with_all_losses

Update the reweighting using losses from a model. Sub-classes should override this method to update the reweighting using lo

src/diffusion/resample.py:107

↓ 1 callersMethodupdate_with_local_losses

Update the reweighting using losses from a model. Call this method from each rank with a batch of timesteps and the correspo

src/diffusion/resample.py:71

↓ 1 callersMethoduvs_to_colors

(self, uvs, tex_ids)

data/mesh_sampler.py:121

↓ 1 callersMethodweights

Get a numpy array of weights, one per diffusion step. The weights needn't be normalized, but must be positive.

src/diffusion/resample.py:35

↓ 1 callersMethodwritekvs

src/diffusion/logger.py:27

↓ 1 callersMethodwriteseq

src/diffusion/logger.py:32

↓ 1 callersFunctionxatlas_uvmap

(mesh_v, mesh_f, resolution)

src/encoding/utils3d.py:228

↓ 1 callersFunctionzero_grad

src/diffusion/fp16_util.py:133

(self, x, ts, **kwargs)

src/diffusion/respace.py:123

data/mesh_sampler.py:12

data/mesh_sampler_pbr.py:14

( self, *, model, use_fp16=False, fp16_scale_growth=1e-3, init

src/diffusion/fp16_util.py:149

(self, diffusion)

src/diffusion/resample.py:62

(self, diffusion, history_per_term=10, uniform_prob=0.001)

src/diffusion/resample.py:125

(self, channels)

src/diffusion/unet_triplane.py:64

src/diffusion/unet_triplane.py:88

src/diffusion/unet_triplane.py:107

src/diffusion/unet_triplane.py:128

( self, channels, emb_channels, dropout=0, out_channels=None,

src/diffusion/unet_triplane.py:192

( self, in_channels, model_channels, out_channels, num_res_blocks=1,

src/diffusion/unet_triplane.py:346

( self, in_channels, model_channels, out_channels, num_res_blocks=1,

src/diffusion/unet_triplane.py:544

(self, filename_or_file)

src/diffusion/logger.py:37

(self, filename)

src/diffusion/logger.py:99

(self, filename)

src/diffusion/logger.py:114

src/diffusion/logger.py:155

(self, dir, output_formats, comm=None)

src/diffusion/logger.py:337

( self, *, betas, model_mean_type, model_var_type, loss_type,

src/diffusion/gaussian_diffusion.py:119

(self, use_timesteps, **kwargs)

src/diffusion/respace.py:72

( self, *, model, diffusion, data, batch_size, microba

src/diffusion/train_util.py:27

(self, x_dim, min_deg, max_deg, use_identity: bool = True)

src/encoding/blocks.py:10

(self, in_channels, out_channels, hidden_channels, num_hidden_layers, posenc=0)

src/encoding/blocks.py:66

(self, in_channels, out_channels=None, dropout=0, up=False, num_groups=8, ks=3, input_norm=True, input_act=Tru

src/encoding/blocks.py:109

(self, in_channels, out_channels, up=False, ks=3, input_norm=True, input_act=True)

src/encoding/blocks.py:190

(self, geo_feat_channels, tex_feat_channels, feat_channel_up, mlp_hidden_channels, mlp_hidden_layers, use_tex=

src/encoding/networks.py:125

(self, geo_feat_channels, tex_feat_channels, feat_channel_up, mlp_hidden_channels, mlp_hidden_layers, use_tex=

src/encoding/networks.py:228

(self, log_dir, args)

src/encoding/model.py:16

(self, ef_dim=32, z_dim=512, class_num=24, voxel_size=128)

evaluation/classifier3D.py:7

evaluation/lpips.py:24

(self, in_channels, out_channels=1)

evaluation/lpips.py:42

Build pretrained InceptionV3 Parameters ---------- output_blocks : list of int Indices of blocks to return featur

evaluation/inception.py:21

Function_compute_statistics_of_path

(files, model, batch_size, dims, cuda)

evaluation/sifid.py:202

Function_find_free_port

src/utils/dist_util.py:71

src/diffusion/unet_triplane.py:269

Method_scale_timesteps

src/diffusion/respace.py:111

Functionavg_pool_nd

Create a 1D, 2D, or 3D average pooling module.

src/diffusion/nn.py:42

(self, loss: th.Tensor)

src/diffusion/fp16_util.py:176

Methodcalc_bpd_loop

Compute the entire variational lower-bound, measured in bits-per-dim, as well as other related quantities. :param model: the

src/diffusion/gaussian_diffusion.py:876

Functioncalculate_sifid_given_paths

Calculates the SIFID of two paths

evaluation/sifid.py:216

src/diffusion/logger.py:93

src/diffusion/logger.py:109

src/diffusion/logger.py:146

src/diffusion/logger.py:185

Methodcondition_mean

(self, cond_fn, *args, **kwargs)

src/diffusion/respace.py:98

Methodcondition_score

(self, cond_fn, *args, **kwargs)

src/diffusion/respace.py:101

Functionconv_nd

Create a 1D, 2D, or 3D convolution module.

src/diffusion/nn.py:22

Functionconvert_module_to_f16

Convert primitive modules to float16.

src/diffusion/fp16_util.py:15

Functionconvert_module_to_f32

Convert primitive modules to float32, undoing convert_module_to_f16().

src/diffusion/fp16_util.py:25

Methodconvert_to_fp16

Convert the torso of the model to float16.

src/diffusion/unet_triplane.py:651

Methodconvert_to_fp32

Convert the torso of the model to float32.

src/diffusion/unet_triplane.py:458

Methodconvert_to_fp32

Convert the torso of the model to float32.

src/diffusion/unet_triplane.py:658

Methodddim_reverse_sample

Sample x_{t+1} from the model using DDIM reverse ODE.

src/diffusion/gaussian_diffusion.py:602

Methodddim_sample_loop

Generate samples from the model using DDIM. Same usage as p_sample_loop().

src/diffusion/gaussian_diffusion.py:640

src/diffusion/logger.py:254

Functiondecorator_with_name

src/diffusion/logger.py:310

Get the device to use for torch.distributed.

src/utils/dist_util.py:45

Functiondumpkvs

Write all of the diagnostics from the current iteration

src/diffusion/logger.py:236

src/diffusion/logger.py:266

src/diffusion/nn.py:18

(ctx, run_function, length, *args)

src/diffusion/nn.py:144

(self, featmaps)

src/diffusion/unet_triplane.py:31

(self, featmaps)

src/diffusion/unet_triplane.py:70

(self, featmaps)

src/diffusion/unet_triplane.py:92

(self, featmaps)

src/diffusion/unet_triplane.py:110

(self, featmaps)

src/diffusion/unet_triplane.py:131

Apply the module to `x` given `emb` timestep embeddings.

src/diffusion/unet_triplane.py:154

src/diffusion/unet_triplane.py:166

Apply the block to a Tensor, conditioned on a timestep embedding. :param x: an [N x C x ...] Tensor of features. :param emb:

src/diffusion/unet_triplane.py:257

Apply the model to an input batch. :param x: an [N x C x ...] Tensor of inputs. :param timesteps: a 1-D batch of timesteps.

src/diffusion/unet_triplane.py:465

Apply the model to an input batch. :param x: an [N x C x ...] Tensor of inputs. :param timesteps: a 1-D batch of timesteps.

src/diffusion/unet_triplane.py:665

Args: x: [..., x_dim] Returns: latent: [..., latent_dim]

src/encoding/blocks.py:26

src/encoding/blocks.py:59

src/encoding/blocks.py:85

src/encoding/blocks.py:95

src/encoding/blocks.py:149

(self, feat_maps)

src/encoding/blocks.py:237

(self, vol, x, aabb=None)

src/encoding/networks.py:119

(self, vol, x, aabb=None)

src/encoding/networks.py:222

(self, vol, x, aabb=None)

src/encoding/networks.py:331

(self, inputs, out_layer=None, is_training=False)

evaluation/classifier3D.py:34

evaluation/lpips.py:32

evaluation/lpips.py:48

evaluation/lpips.py:75

Get Inception feature maps Parameters ---------- inp : torch.autograd.Variable Input tensor of shape Bx3xHxW. Val

evaluation/inception.py:113

Functionfunc_wrapper

(*args, **kwargs)

src/diffusion/logger.py:311

Methodgeo_parameters

src/encoding/networks.py:151

Methodgeo_parameters

src/encoding/networks.py:257

Functionget_dir

Get directory that log files are being written to. will be None if there is no output directory (i.e., if you didn't call start)

src/diffusion/logger.py:281

← previous next →201–300 of 339, ranked by callers