Functions — github.com/Vanessik/HAAR

CodeHub MCPcopy Create free account

hub / github.com/Vanessik/HAAR / functions

Functions176 in github.com/Vanessik/HAAR

⨍ Functions 176◇ Types & classes 41

(self, dim, dim_out=None, mult=4, glu=False, dropout=0.)

src/utils/attention.py:50

(self, dim, heads=4, dim_head=32)

src/utils/attention.py:83

(self, in_channels)

src/utils/attention.py:102

(self, query_dim, context_dim=None, heads=8, dim_head=64, dropout=0.)

src/utils/attention.py:155

(self, dim, n_heads, d_head, dropout=0., context_dim=None, gated_ff=True, checkpoint=True)

src/utils/attention.py:199

(self, in_channels, n_heads, d_head, depth=1, dropout=0., context_dim=None)

src/utils/attention.py:228

(self, c_concat_config, c_crossattn_config)

src/utils/util.py:264

(self, mode='mixed', use_noise=True, noise_mean=0.15,

src/upsampling/upsampler.py:11

(self, device='cuda', path_to_data='./dataset/pointclouds', sc

src/datasets/aug_dataset.py:18

(self, device='cuda', path_to_data='./dataset/pointclouds',

src/datasets/dataset.py:21

src/datasets/dataset.py:187

src/openaimodel.py:256

src/openaimodel.py:319

(self, x, context=None)

src/utils/attention.py:213

Method_weighting_snr

src/utils/layers.py:71

Method_weighting_soft_min_snr

src/utils/layers.py:68

Functionbetas_for_alpha_bar

Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [

src/utils/util.py:88

Functioncheck_barycentric_weights

(barycentric_weights)

src/utils/geometry.py:88

Functionconvert_module_to_f16

src/openaimodel.py:25

Functionconvert_module_to_f32

src/openaimodel.py:28

Methodconvert_to_fp16

Convert the torso of the model to float16.

src/openaimodel.py:713

Methodconvert_to_fp16

Convert the torso of the model to float16.

src/openaimodel.py:939

Methodconvert_to_fp32

Convert the torso of the model to float32.

src/openaimodel.py:721

Methodconvert_to_fp32

Convert the torso of the model to float32.

src/openaimodel.py:946

Methodcount_flops

src/openaimodel.py:376

Methodcount_flops

src/openaimodel.py:410

Functionensure_distributed

Functionextract_into_tensor

(a, t, x_shape)

src/utils/util.py:107

src/openaimodel.py:52

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

src/openaimodel.py:69

(self, x, emb, context=None)

src/openaimodel.py:81

src/openaimodel.py:110

src/openaimodel.py:131

src/openaimodel.py:159

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

src/openaimodel.py:244

src/openaimodel.py:315

Apply QKV attention. :param qkv: an [N x (H * 3 * C) x T] tensor of Qs, Ks, and Vs. :return: an [N x (H * C) x T] tensor afte

src/openaimodel.py:357

Apply QKV attention. :param qkv: an [N x (3 * H * C) x T] tensor of Qs, Ks, and Vs. :return: an [N x (H * C) x T] tensor afte

src/openaimodel.py:389

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/openaimodel.py:729

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/openaimodel.py:953

(self, input, sigma, **kwargs)

src/utils/layers.py:102

src/utils/layers.py:147

(self, input, cond=None)

src/utils/layers.py:162

(self, input, cond)

src/utils/layers.py:167

(self, input, cond)

src/utils/layers.py:182

(self, input, cond)

src/utils/layers.py:197

(self, input, cond)

src/utils/layers.py:218

(self, input, cond)

src/utils/layers.py:247

src/utils/layers.py:297

src/utils/layers.py:313

src/utils/layers.py:329

(self, input, cond)

src/utils/layers.py:343

src/utils/attention.py:44

src/utils/attention.py:65

src/utils/attention.py:90

src/utils/attention.py:128

(self, x, context=None, mask=None)

src/utils/attention.py:172

(self, x, context=None)

src/utils/attention.py:210

(self, x, context=None)

src/utils/attention.py:252

(ctx, run_function, length, *args)

src/utils/util.py:132

src/utils/util.py:226

(self, c_concat, c_crossattn)

src/utils/util.py:269

Upsample initial sparse guiding strands to desired resolution Input: texture = [1, 64, patch_size, patch_size]

src/upsampling/upsampler.py:98

Functionget_chunk

preprocess_dataset/obtain_hairstyle_descriptions.py:30

src/utils/attention.py:31

(self, input, noise, sigma, mask, **kwargs)

src/utils/layers.py:108

(self, input, noise, sigma, mask, **kwargs)

src/utils/layers.py:129

Functionmake_beta_schedule

(schedule, n_timestep, linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3)

src/utils/util.py:32

Functionmake_ddim_sampling_parameters

(alphacums, ddim_timesteps, eta, verbose=True)

src/utils/util.py:74

Functionmake_ddim_timesteps

(ddim_discr_method, num_ddim_timesteps, num_ddpm_timesteps, verbose=True)

src/utils/util.py:57

Functionmax_neg_value

src/utils/attention.py:27

Functionmean_flat

Take the mean over all non-batch dimensions.

src/utils/util.py:203

Functionnoise_like

(shape, device, repeat=False)

src/utils/util.py:275

Methodparam_groups

(self, base_lr=2e-4)

src/openaimodel.py:695

Functionscale_module

Scale the parameters of a module and return it.

src/utils/util.py:194

src/utils/attention.py:17

← previous101–176 of 176, ranked by callers