MCPcopy Create free account

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

Functions543 in github.com/cientgu/VQ-Diffusion

⨍ Functions 543◇ Types & classes 107
↓ 48 callersMethodget
(self, key, func=None)
image_synthesis/data/utils/manage.py:410
↓ 32 callersFunctioninstantiate_from_config
(config)
image_synthesis/utils/misc.py:125
↓ 25 callersMethodkeys
(self)
image_synthesis/data/utils/manage.py:399
↓ 22 callersMethodload_state_dict
(self, state_dict, strict=True)
image_synthesis/engine/ema.py:42
↓ 19 callersMethodstate_dict
(self)
image_synthesis/engine/ema.py:39
↓ 18 callersMethodlog_info
(self, info, check_primary=True)
image_synthesis/engine/logger.py:48
↓ 17 callersMethodeval
(self)
image_synthesis/taming/modules/misc/coord.py:8
↓ 16 callersMethodparameters
(self, recurse=True, name=None)
image_synthesis/modeling/models/dalle.py:37
↓ 14 callersMethodupdate
(self, iteration)
image_synthesis/engine/ema.py:26
↓ 13 callersMethoddecode
(self, tokens)
image_synthesis/modeling/modules/clip/clip_tokenizer.py:133
↓ 11 callersFunctionnonlinearity
(x)
image_synthesis/taming/modules/diffusionmodules/model.py:29
↓ 10 callersFunctionNormalize
(in_channels)
image_synthesis/taming/modules/diffusionmodules/model.py:34
↓ 10 callersMethod__init__
(self)
image_synthesis/modeling/transformers/transformer_utils.py:114
↓ 10 callersFunctionextract
(a, t, x_shape)
image_synthesis/modeling/transformers/diffusion_transformer.py:33
↓ 10 callersFunctionextract
(a, t, x_shape)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:26
↓ 10 callersMethodget_tokens
Input: x: input data Return: indices: B x L, the codebook indices, where L is the length
image_synthesis/modeling/codecs/base_codec.py:7
↓ 10 callersMethodopen
(self)
image_synthesis/data/utils/manage.py:241
↓ 9 callersMethod__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:196
↓ 8 callersMethodget_last_layer
(self)
image_synthesis/taming/models/vqgan.py:133
↓ 8 callersMethodis_initialized
(self)
image_synthesis/taming/modules/transformer/mingpt.py:333
↓ 8 callersFunctionlog_onehot_to_index
(log_x)
image_synthesis/modeling/transformers/diffusion_transformer.py:50
↓ 8 callersFunctionlog_onehot_to_index
(log_x)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:43
↓ 7 callersMethod__init__
(self, H, W)
image_synthesis/taming/modules/transformer/permuter.py:63
↓ 7 callersMethodclose
(self)
image_synthesis/engine/logger.py:85
↓ 7 callersMethoddecode
(self, quant)
image_synthesis/taming/models/vqgan.py:61
↓ 7 callersMethodget_ema_model
(self)
image_synthesis/modeling/models/dalle.py:54
↓ 6 callersMethod__init__
(self, embed_dim: int, # vision image_resolution: int,
image_synthesis/modeling/modules/clip/model.py:239
↓ 6 callersMethodget_input
(self, batch, k)
image_synthesis/taming/models/vqgan.py:76
↓ 6 callersFunctionlog_add_exp
(a, b)
image_synthesis/modeling/transformers/diffusion_transformer.py:29
↓ 6 callersFunctionlog_add_exp
(a, b)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:22
↓ 6 callersMethodtrain
(self, mode=True)
image_synthesis/modeling/codecs/base_codec.py:32
↓ 5 callersMethod__init__
(self, vocab_size, block_size, n_layer=12, n_head=8, n_embd=256, embd_pdrop=0., resid_pdrop=0
image_synthesis/taming/modules/transformer/mingpt.py:126
↓ 5 callersFunctionformat_seconds
(seconds)
image_synthesis/utils/misc.py:103
↓ 5 callersMethodq_posterior
(self, log_x_start, log_x_t, t)
image_synthesis/modeling/transformers/diffusion_transformer.py:206
↓ 5 callersMethodq_posterior
(self, log_x_start, log_x_t, t)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:213
↓ 4 callersMethod__init__
(self, encoder, quant_conv, quantize)
image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:18
↓ 4 callersMethod_make_layer
(self, planes, blocks, stride=1)
image_synthesis/modeling/modules/clip/model.py:125
↓ 4 callersMethoddecode_to_img
(self, index, zshape)
image_synthesis/taming/models/cond_transformer.py:185
↓ 4 callersMethoddevice
(self)
image_synthesis/modeling/models/dalle.py:51
↓ 4 callersMethodencode
(self, x)
image_synthesis/taming/models/vqgan.py:55
↓ 4 callersFunctionget_world_size
()
image_synthesis/distributed/distributed.py:54
↓ 4 callersMethodpredict_start
(self, log_x_t, cond_emb, t)
image_synthesis/modeling/transformers/diffusion_transformer.py:186
↓ 4 callersMethodpredict_start
(self, log_x_t, cond_emb, t)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:194
↓ 4 callersFunctionpreload
(db,sync=True,load=True)
image_synthesis/data/utils/manage.py:76
↓ 4 callersMethodprepare_condition
(self, batch)
image_synthesis/modeling/models/conditional_dalle.py:57
↓ 4 callersMethodprepare_condition
(self, batch, condition=None)
image_synthesis/modeling/models/dalle.py:58
↓ 4 callersMethodsave
(self, force=False)
image_synthesis/engine/solver.py:300
↓ 4 callersMethodto_rgb
(self, x)
image_synthesis/taming/models/vqgan.py:150
↓ 3 callersMethod__init__
(self, num_features, logdet=False, affine=True, allow_reverse_init=False)
image_synthesis/taming/modules/util.py:11
↓ 3 callersMethod__init__
(self, use_dropout=True)
image_synthesis/taming/modules/losses/lpips.py:13
↓ 3 callersMethod_set_trainable
(self)
image_synthesis/modeling/embeddings/base_embedding.py:19
↓ 3 callersMethod_set_trainable
(self)
image_synthesis/modeling/codecs/base_codec.py:39
↓ 3 callersMethodadd_scalar
Log a scalar variable.
image_synthesis/engine/logger.py:60
↓ 3 callersMethodget_xc
(self, batch, N=None)
image_synthesis/taming/models/cond_transformer.py:275
↓ 3 callersMethodhead
(self)
image_synthesis/data/utils/comm.py:53
↓ 3 callersFunctionindex_to_log_onehot
(x, num_classes)
image_synthesis/modeling/transformers/diffusion_transformer.py:41
↓ 3 callersFunctionindex_to_log_onehot
(x, num_classes)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:34
↓ 3 callersMethodlog_sample_categorical
(self, logits)
image_synthesis/modeling/transformers/diffusion_transformer.py:257
↓ 3 callersMethodlog_sample_categorical
(self, logits)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:262
↓ 3 callersMethodq_pred
(self, log_x_start, t)
image_synthesis/modeling/transformers/diffusion_transformer.py:167
↓ 3 callersMethodq_pred
(self, log_x_start, t)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:179
↓ 3 callersMethodsample
(self, x, c, steps, temperature=1.0, sample=False, top_k=None, callback=lambda k: None)
image_synthesis/taming/models/cond_transformer.py:113
↓ 3 callersFunctionsum_except_batch
(x, num_dims=1)
image_synthesis/modeling/transformers/diffusion_transformer.py:23
↓ 3 callersFunctionsum_except_batch
(x, num_dims=1)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:16
↓ 3 callersMethodtrain
(self)
image_synthesis/engine/solver.py:540
↓ 2 callersMethod__init__
(self, num_hiddens, embedding_dim, n_embed, straight_through=True, kl_weight=5e-4, temp_init=
image_synthesis/taming/modules/vqvae/quantize.py:117
↓ 2 callersMethod_get_lr
(self, return_type='str')
image_synthesis/engine/solver.py:163
↓ 2 callersMethod_init_is_better
(self, mode, threshold, threshold_mode)
image_synthesis/engine/lr_scheduler.py:184
↓ 2 callersMethod_prepare_for_warmup
(self)
image_synthesis/engine/lr_scheduler.py:269
↓ 2 callersFunction_transform
(n_px)
image_synthesis/modeling/modules/clip/clip.py:57
↓ 2 callersFunctionadopt_weight
(weight, global_step, threshold=0, value=0.)
image_synthesis/taming/modules/losses/vqperceptual.py:14
↓ 2 callersFunctionbuild_model
(config, args=None)
image_synthesis/modeling/build.py:4
↓ 2 callersFunctionbytes_to_unicode
Returns list of utf-8 byte and a corresponding list of unicode strings. The reversible bpe codes work on unicode strings. This means you
image_synthesis/modeling/modules/clip/simple_tokenizer.py:16
↓ 2 callersFunctionbytes_to_unicode
Returns list of utf-8 byte and a corresponding list of unicode strings. The reversible bpe codes work on unicode strings. This means you
image_synthesis/modeling/modules/clip/clip_tokenizer.py:16
↓ 2 callersMethodencode_to_c
(self, c)
image_synthesis/taming/models/cond_transformer.py:176
↓ 2 callersMethodencode_to_z
(self, x)
image_synthesis/taming/models/cond_transformer.py:169
↓ 2 callersMethodgenerate_content
( self, *, batch, condition=None, filter_ratio = 0.5, temperat
image_synthesis/modeling/models/dalle.py:140
↓ 2 callersMethodget_block_size
(self)
image_synthesis/taming/modules/transformer/mingpt.py:147
↓ 2 callersFunctionget_ckpt_path
(name, root, check=False)
image_synthesis/taming/util.py:36
↓ 2 callersMethodget_codebook_entry
(self, indices, shape)
image_synthesis/taming/modules/vqvae/quantize.py:202
↓ 2 callersMethodget_input
(self, key, batch)
image_synthesis/taming/models/cond_transformer.py:265
↓ 2 callersFunctionget_keys_from_lmdb
(db)
image_synthesis/data/utils/manage.py:87
↓ 2 callersFunctionget_model_parameters_info
(model)
image_synthesis/utils/misc.py:57
↓ 2 callersFunctionget_pairs
Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings).
image_synthesis/modeling/modules/clip/simple_tokenizer.py:38
↓ 2 callersFunctionget_pairs
Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings).
image_synthesis/modeling/modules/clip/clip_tokenizer.py:38
↓ 2 callersFunctionget_rank
()
image_synthesis/distributed/distributed.py:16
↓ 2 callersFunctionget_timestep_embedding
This matches the implementation in Denoising Diffusion Probabilistic Models: From Fairseq. Build sinusoidal embeddings. This matches
image_synthesis/taming/modules/diffusionmodules/model.py:8
↓ 2 callersMethodinit_from_ckpt
(self, path, ignore_keys=list())
image_synthesis/taming/models/vqgan.py:44
↓ 2 callersMethodinitialize
(self, input)
image_synthesis/taming/modules/util.py:22
↓ 2 callersFunctionis_primary
()
image_synthesis/distributed/distributed.py:12
↓ 2 callersFunctionload_yaml_config
(path)
image_synthesis/utils/io.py:6
↓ 2 callersFunctionlog_1_min_a
(a)
image_synthesis/modeling/transformers/diffusion_transformer.py:26
↓ 2 callersFunctionlog_1_min_a
(a)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:19
↓ 2 callersFunctionmap_name
(file)
image_synthesis/data/utils/manage.py:68
↓ 2 callersFunctionmd5_hash
(path)
image_synthesis/taming/util.py:30
↓ 2 callersMethodmultinomial_kl
(self, log_prob1, log_prob2)
image_synthesis/modeling/transformers/diffusion_transformer.py:147
↓ 2 callersMethodmultinomial_kl
(self, log_prob1, log_prob2)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:163
↓ 2 callersFunctionnormalize_tensor
(x,eps=1e-10)
image_synthesis/taming/modules/losses/lpips.py:114
↓ 2 callersMethodp_sample
(self, log_x, cond_emb, t)
image_synthesis/modeling/transformers/diffusion_transformer.py:252
↓ 2 callersMethodp_sample
(self, log_x, cond_emb, t)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:257
next →1–100 of 543, ranked by callers