MCPcopy Create free account

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

Functions543 in github.com/cientgu/VQ-Diffusion

⨍ Functions 543◇ Types & classes 107
Method__init__
(self, *, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks, attn_resolutions, dropout=0.0, resam
image_synthesis/taming/modules/diffusionmodules/model.py:343
Method__init__
(self, *, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks, attn_resolutions, dropout=0.0, resam
image_synthesis/taming/modules/diffusionmodules/model.py:437
Method__init__
(self, *, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks, attn_resolutions, dropout=0.0, resam
image_synthesis/taming/modules/diffusionmodules/model.py:541
Method__init__
(self, in_channels, out_channels, *args, **kwargs)
image_synthesis/taming/modules/diffusionmodules/model.py:695
Method__init__
(self, in_channels, out_channels, ch, num_res_blocks, resolution, ch_mult=(2,2), dropout=0.0)
image_synthesis/taming/modules/diffusionmodules/model.py:731
Method__init__
Construct a PatchGAN discriminator Parameters: input_nc (int) -- the number of channels in input images ndf (int)
image_synthesis/taming/modules/discriminator/model.py:21
Method__init__
(self, n_e, e_dim, beta)
image_synthesis/taming/modules/vqvae/quantize.py:25
Method__init__
(self, n_e, e_dim, beta, remap=None, unknown_index="random", sane_index_shape=False, legacy=T
image_synthesis/taming/modules/vqvae/quantize.py:221
Method__init__
(self, n_embed, down_factor)
image_synthesis/taming/modules/misc/coord.py:4
Method__init__
(self, vocab_size, block_size, **kwargs)
image_synthesis/taming/modules/transformer/mingpt.py:27
Method__init__
(self, config)
image_synthesis/taming/modules/transformer/mingpt.py:48
Method__init__
(self, config)
image_synthesis/taming/modules/transformer/mingpt.py:99
Method__init__
(self, add_value=1)
image_synthesis/taming/modules/transformer/mingpt.py:216
Method__init__
(self, vocab_size, block_size, in_channels, n_layer=12, n_head=8, n_embd=256, embd_pdrop=0.,
image_synthesis/taming/modules/transformer/mingpt.py:226
Method__init__
(self, ncluster=512, nc=3, niter=10)
image_synthesis/taming/modules/transformer/mingpt.py:324
Method__init__
(self, *args, **kwargs)
image_synthesis/taming/modules/transformer/permuter.py:7
Method__init__
(self)
image_synthesis/taming/modules/transformer/permuter.py:14
Method__init__
(self, H, W)
image_synthesis/taming/modules/transformer/permuter.py:22
Method__init__
(self, H, W)
image_synthesis/taming/modules/transformer/permuter.py:82
Method__init__
(self, H, W)
image_synthesis/taming/modules/transformer/permuter.py:142
Method__init__
(self, H, W)
image_synthesis/taming/modules/transformer/permuter.py:203
Method__init__
(self, H, W)
image_synthesis/taming/modules/transformer/permuter.py:218
Method__init__
(self, disc_start, codebook_weight=1.0, pixelloss_weight=1.0, disc_num_layers=3, disc_in_chan
image_synthesis/taming/modules/losses/vqperceptual.py:35
Method__init__
(self)
image_synthesis/taming/modules/losses/lpips.py:56
Method__init__
(self, chn_in, chn_out=1, use_dropout=False)
image_synthesis/taming/modules/losses/lpips.py:67
Method__init__
(self, requires_grad=False, pretrained=True)
image_synthesis/taming/modules/losses/lpips.py:75
Method__init__
(self, codebook_weight=1.)
image_synthesis/taming/modules/losses/segmentation.py:12
Method__init__
(self, ddconfig, lossconfig, n_embed, embe
image_synthesis/taming/models/vqgan.py:160
Method__init__
(self, transformer_config, first_stage_config, cond_stage_c
image_synthesis/taming/models/cond_transformer.py:17
Method__len__
(self)
image_synthesis/data/cub200_dataset.py:39
Method__len__
(self)
image_synthesis/data/mscoco_dataset.py:30
Method__len__
(self)
image_synthesis/data/utils/manage.py:259
Method__repr__
(self)
image_synthesis/modeling/codecs/text_codec/tokenize.py:51
Function_convert_weights_to_fp16
(l)
image_synthesis/modeling/modules/clip/model.py:376
Function_download
(url: str, root: str = os.path.expanduser("~/.cache/image-synthesis"))
image_synthesis/modeling/modules/clip/clip.py:24
Method_init_weights
(self, module)
image_synthesis/modeling/transformers/transformer_utils.py:355
Method_init_weights
(self, module)
image_synthesis/modeling/transformers/transformer_utils.py:499
Method_init_weights
(self, module)
image_synthesis/modeling/transformers/transformer_utils.py:639
Method_init_weights
(self, module)
image_synthesis/taming/modules/transformer/mingpt.py:150
Method_init_weights
(self, module)
image_synthesis/taming/modules/transformer/mingpt.py:250
Methodadd_image
Log a scalar variable.
image_synthesis/engine/logger.py:72
Methodadd_scalars
Log a scalar variable.
image_synthesis/engine/logger.py:66
Functionall_gather
(data)
image_synthesis/distributed/distributed.py:79
Functionall_gather
Run all_gather on arbitrary picklable data (not necessarily tensors) Args: data: any picklable object Returns: list[data]
image_synthesis/data/utils/comm.py:72
Functionall_reduce
(tensor, op=dist.ReduceOp.SUM, async_op=False)
image_synthesis/distributed/distributed.py:69
Methodcheck_length
(self, token)
image_synthesis/modeling/codecs/text_codec/tokenize.py:56
Functionclass_from_string
(class_name)
image_synthesis/utils/misc.py:134
Methodcleanup
(self)
image_synthesis/data/utils/manage.py:369
Methodconfigure_optimizers
(self)
image_synthesis/taming/models/vqgan.py:121
Methodconfigure_optimizers
Following minGPT: This long function is unfortunately doing something very simple and is being very defensive: We are separat
image_synthesis/taming/models/cond_transformer.py:299
Functioncount_params
(model)
image_synthesis/taming/modules/util.py:5
Functiondata_sampler
(dataset, shuffle, distributed)
image_synthesis/distributed/distributed.py:139
Methoddecode
(self, img_seq)
image_synthesis/modeling/codecs/base_codec.py:26
Methoddecode
(self, img_seq)
image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:121
Methoddecode
(self, img_seq)
image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:200
Methoddecode
(self, img_seq)
image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:278
Methoddecode
(self, c)
image_synthesis/taming/modules/misc/coord.py:27
Methoddecode_code
(self, code_b)
image_synthesis/taming/models/vqgan.py:66
Methoddecode_code
(self, code_b)
image_synthesis/taming/models/vqgan.py:208
Functiondecode_img
(byteflow)
image_synthesis/data/utils/manage.py:91
Methoddecode_int
(self,num_bytes)
image_synthesis/data/utils/manage.py:407
Functiondecode_text
(byteflow)
image_synthesis/data/utils/manage.py:96
Methoddevice
(self)
image_synthesis/modeling/transformers/diffusion_transformer.py:364
Methoddevice
(self)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:369
Methoddevice
(self)
image_synthesis/modeling/models/unconditional_dalle.py:47
Methoddevice
(self)
image_synthesis/modeling/models/conditional_dalle.py:50
Methoddevice
(self)
image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:93
Methoddevice
(self)
image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:172
Methoddevice
(self)
image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:250
Functiondisabled_train
Overwrite model.train with this function to make sure train/eval mode does not change anymore.
image_synthesis/taming/models/cond_transformer.py:10
Functiondistributed_worker
( local_rank, fn, world_size, n_gpu_per_machine, machine_rank, dist_url, args )
image_synthesis/distributed/launch.py:53
Methoddtype
(self)
image_synthesis/modeling/embeddings/clip_text_embedding.py:43
Methoddtype
(self)
image_synthesis/modeling/modules/clip/model.py:332
Methodencode
(self, text)
image_synthesis/modeling/modules/clip/simple_tokenizer.py:125
Methodencode
(self, img)
image_synthesis/modeling/codecs/base_codec.py:23
Methodencode
(self, *args, **kwargs)
image_synthesis/taming/modules/util.py:99
Methodencode
(self, c)
image_synthesis/taming/modules/util.py:110
Methodencode
(self, x)
image_synthesis/taming/modules/util.py:124
Methodencode
fake vqmodel interface
image_synthesis/taming/modules/misc/coord.py:11
Methodencode_int
(self,num)
image_synthesis/data/utils/manage.py:404
Methodencode_to_prequant
(self, x)
image_synthesis/taming/models/vqgan.py:203
Methodforward
index: B x L, index mask: B x L, bool type. The value of False indicating padded index
image_synthesis/modeling/embeddings/class_embedding.py:22
Methodforward
(self, index, **kwargs)
image_synthesis/modeling/embeddings/dalle_mask_image_embedding.py:37
Methodforward
index: B x L, index mask: B x L, bool type. The value of False indicating padded index
image_synthesis/modeling/embeddings/clip_text_embedding.py:66
Methodforward
(self, **kwargs)
image_synthesis/modeling/embeddings/base_embedding.py:10
Methodforward
(self, x: torch.Tensor)
image_synthesis/modeling/modules/clip/model.py:39
Methodforward
(self, x)
image_synthesis/modeling/modules/clip/model.py:65
Methodforward
(self, x)
image_synthesis/modeling/modules/clip/model.py:134
Methodforward
(self, x: torch.Tensor)
image_synthesis/modeling/modules/clip/model.py:155
Methodforward
(self, x: torch.Tensor)
image_synthesis/modeling/modules/clip/model.py:162
Methodforward
(self, x: torch.Tensor)
image_synthesis/modeling/modules/clip/model.py:184
Methodforward
(self, x: torch.Tensor)
image_synthesis/modeling/modules/clip/model.py:197
Methodforward
(self, x: torch.Tensor)
image_synthesis/modeling/modules/clip/model.py:218
Methodforward
( self, input, return_loss=False, return_logits=True,
image_synthesis/modeling/transformers/diffusion_transformer.py:423
Methodforward
( self, input, return_loss=False, return_logits=True,
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:428
Methodforward
(self, x, encoder_output, mask=None)
image_synthesis/modeling/transformers/transformer_utils.py:45
Methodforward
(self, x, encoder_output, mask=None)
image_synthesis/modeling/transformers/transformer_utils.py:93
Methodforward
(self, x)
image_synthesis/modeling/transformers/transformer_utils.py:116
Methodforward
(self, x)
image_synthesis/modeling/transformers/transformer_utils.py:126
Methodforward
(self, x, timestep)
image_synthesis/modeling/transformers/transformer_utils.py:147
← previousnext →301–400 of 543, ranked by callers