Functions — github.com/cientgu/VQ-Diffusion

CodeHub MCPcopy Create free account

hub / github.com/cientgu/VQ-Diffusion / functions

Functions543 in github.com/cientgu/VQ-Diffusion

⨍ Functions 543◇ Types & classes 107

(self, x, timestep)

image_synthesis/modeling/transformers/transformer_utils.py:164

(self, x, encoder_output, timestep, mask=None)

image_synthesis/modeling/transformers/transformer_utils.py:257

image_synthesis/modeling/transformers/transformer_utils.py:284

( self, input, cond_emb, t)

image_synthesis/modeling/transformers/transformer_utils.py:421

( self, input, cond_emb, t)

image_synthesis/modeling/transformers/transformer_utils.py:566

( self, input, cond_emb, t)

image_synthesis/modeling/transformers/transformer_utils.py:706

( self, batch, name='none', **kwargs )

image_synthesis/modeling/models/unconditional_dalle.py:216

( self, batch, name='none', **kwargs )

image_synthesis/modeling/models/conditional_dalle.py:263

( self, batch, name='none', **kwargs )

image_synthesis/modeling/models/dalle.py:291

(self, **kwargs)

image_synthesis/modeling/codecs/base_codec.py:29

image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:25

(self, indices)

image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:42

(self, input, reverse=False)

image_synthesis/taming/modules/util.py:43

image_synthesis/taming/modules/diffusionmodules/model.py:49

image_synthesis/taming/modules/diffusionmodules/model.py:68

(self, x, temb)

image_synthesis/taming/modules/diffusionmodules/model.py:117

image_synthesis/taming/modules/diffusionmodules/model.py:168

(self, x, t=None)

image_synthesis/taming/modules/diffusionmodules/model.py:295

image_synthesis/taming/modules/diffusionmodules/model.py:406

image_synthesis/taming/modules/diffusionmodules/model.py:506

image_synthesis/taming/modules/diffusionmodules/model.py:645

image_synthesis/taming/modules/diffusionmodules/model.py:717

image_synthesis/taming/modules/diffusionmodules/model.py:764

Standard forward.

image_synthesis/taming/modules/discriminator/model.py:65

Inputs the output of the encoder network z and maps it to a discrete one-hot vector that is the index of the closest embedding vector

image_synthesis/taming/modules/vqvae/quantize.py:34

(self, z, temp=None, return_logits=False)

image_synthesis/taming/modules/vqvae/quantize.py:171

(self, z, temp=None, rescale_logits=False, return_logits=False)

image_synthesis/taming/modules/vqvae/quantize.py:271

(self, x, layer_past=None)

image_synthesis/taming/modules/transformer/mingpt.py:68

(self, x, layer_past=None, return_present=False)

image_synthesis/taming/modules/transformer/mingpt.py:111

(self, idx, embeddings=None, targets=None)

image_synthesis/taming/modules/transformer/mingpt.py:159

image_synthesis/taming/modules/transformer/mingpt.py:220

(self, idx, embeddings=None, targets=None)

image_synthesis/taming/modules/transformer/mingpt.py:259

(self, x, reverse=False, shape=None)

image_synthesis/taming/modules/transformer/mingpt.py:356

(self, x, reverse=False)

image_synthesis/taming/modules/transformer/permuter.py:9

(self, x, reverse=False)

image_synthesis/taming/modules/transformer/permuter.py:17

(self, x, reverse=False)

image_synthesis/taming/modules/transformer/permuter.py:40

(self, x, reverse=False)

image_synthesis/taming/modules/transformer/permuter.py:74

(self, x, reverse=False)

image_synthesis/taming/modules/transformer/permuter.py:134

(self, x, reverse=False)

image_synthesis/taming/modules/transformer/permuter.py:195

(self, x, reverse=False)

image_synthesis/taming/modules/transformer/permuter.py:210

(self, x, reverse=False)

image_synthesis/taming/modules/transformer/permuter.py:229

(self, codebook_loss, inputs, reconstructions, optimizer_idx, global_step, last_layer=None, co

image_synthesis/taming/modules/losses/vqperceptual.py:76

(self, input, target)

image_synthesis/taming/modules/losses/lpips.py:39

image_synthesis/taming/modules/losses/lpips.py:61

image_synthesis/taming/modules/losses/lpips.py:98

(self, prediction, target)

image_synthesis/taming/modules/losses/segmentation.py:6

(self, qloss, target, prediction, split)

image_synthesis/taming/modules/losses/segmentation.py:16

image_synthesis/taming/models/vqgan.py:71

image_synthesis/taming/models/cond_transformer.py:80

Methodforward_with_past

(self, idx, embeddings=None, targets=None, past=None, past_length=None)

image_synthesis/taming/modules/transformer/mingpt.py:181

Methodfrom_pretrained

(cls, name="vgg_lpips")

image_synthesis/taming/modules/losses/lpips.py:33

Functiongather_nearby_tensors

Performs all_gather operation on the provided tensors. *** Warning ***: torch.distributed.all_gather has no gradient.

image_synthesis/data/utils/comm.py:177

Functiongather_tensors

Performs all_gather operation on the provided tensors. *** Warning ***: torch.distributed.all_gather has no gradient.

image_synthesis/data/utils/comm.py:144

Functiongather_tensors_fake

Performs all_gather operation on the provided tensors. *** Warning ***: torch.distributed.all_gather has no gradient.

image_synthesis/data/utils/comm.py:160

Functiongather_tensors_with_gradient

collect all tensor from all GPUs args: x: shape (mini_batch, ...) returns: shape (mini_batch * num_gpu, ...)

image_synthesis/data/utils/comm.py:199

Functiongen_attention_mask

(H, W, type='full', causal=True, condition_seq_len=0, **kwargs)

image_synthesis/modeling/utils/misc.py:101

Methodgenerate_content

( self, *, batch, filter_ratio = 0.5, temperature = 1.0, conte

image_synthesis/modeling/models/unconditional_dalle.py:109

Methodgenerate_content

( self, *, batch, condition=None, filter_ratio = 0.5, temperat

image_synthesis/modeling/models/conditional_dalle.py:123

image_synthesis/data/utils/manage.py:152

image_synthesis/data/utils/manage.py:202

image_synthesis/data/utils/manage.py:251

(self, name,source=None)

image_synthesis/data/utils/manage.py:373

Functionget_all_file

(dir, end_with='.h5')

image_synthesis/utils/misc.py:139

Methodget_block_size

image_synthesis/taming/modules/transformer/mingpt.py:247

Methodget_codebook_entry

(self, indices, shape)

image_synthesis/taming/modules/vqvae/quantize.py:92

Methodget_codebook_entry

(self, indices, shape)

image_synthesis/taming/modules/vqvae/quantize.py:314

Methodget_ema_model

image_synthesis/modeling/models/unconditional_dalle.py:50

Methodget_ema_model

image_synthesis/modeling/models/conditional_dalle.py:53

Functionget_local_rank

image_synthesis/distributed/distributed.py:26

image_synthesis/modeling/embeddings/base_embedding.py:7

Functionget_model_buffer

image_synthesis/utils/misc.py:159

Methodget_number_of_tokens

Return: int, the number of tokens

image_synthesis/modeling/codecs/base_codec.py:17

Functionget_sub_dirs

(dir, abs=True)

image_synthesis/utils/misc.py:152

Functionget_token_type

Get the token type according to the given mask and token_shape. Note that we treat tokens into 3 types. 0: masked tokens 1: unmasked

image_synthesis/modeling/utils/misc.py:75

Methodget_tokens

(self, imgs, **kwargs)

image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:112

Methodget_tokens

(self, imgs, **kwargs)

image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:191

Methodget_tokens

(self, imgs, **kwargs)

image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:269

Methodget_tokens

(self, text, **kwargs)

image_synthesis/modeling/codecs/text_codec/tokenize.py:59

Functionhinge_d_loss

(logits_real, logits_fake)

image_synthesis/taming/modules/losses/vqperceptual.py:20

Functionin_blob

image_synthesis/data/utils/manage.py:62

Methodin_cooldown

image_synthesis/engine/lr_scheduler.py:166

Methodinference_generate_sample_with_condition

(self, text, truncation_rate, save_root, batch_size,fast=False)

inference_VQ_Diffusion.py:98

Methodinitialize

image_synthesis/data/utils/manage.py:178

Methodinitialize

image_synthesis/taming/modules/transformer/mingpt.py:337

Functionis_distributed

image_synthesis/distributed/distributed.py:64

Methodis_main_process

image_synthesis/data/utils/comm.py:56

Methodkeep_subset

image_synthesis/data/utils/manage.py:297

image_synthesis/data/utils/manage.py:147

image_synthesis/data/utils/manage.py:193

image_synthesis/data/utils/manage.py:246

image_synthesis/data/utils/manage.py:364

Load a CLIP model Parameters ---------- name : str A model name listed by `clip.available_models()`, or the path to a model check

image_synthesis/modeling/modules/clip/clip.py:72

Functionload_dict_from_json

image_synthesis/utils/io.py:22

Methodload_state_dict

(self, state_dict)

image_synthesis/engine/clip_grad_norm.py:30

Methodload_state_dict

(self, state_dict)

image_synthesis/engine/lr_scheduler.py:204

Methodload_state_dict

(self, state_dict)

image_synthesis/engine/lr_scheduler.py:290

Methodlocal_rank

image_synthesis/data/utils/comm.py:34

Methodlog_images

(self, batch, **kwargs)

image_synthesis/taming/models/vqgan.py:136

Methodlog_images

(self, batch, **kwargs)

image_synthesis/taming/models/vqgan.py:249

Methodlog_images

(self, batch, temperature=None, top_k=None, callback=None, lr_interface=False, **kwargs)

image_synthesis/taming/models/cond_transformer.py:194

← previous next →401–500 of 543, ranked by callers