MCPcopy Create free account

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

Functions543 in github.com/cientgu/VQ-Diffusion

⨍ Functions 543◇ Types & classes 107
↓ 2 callersMethodparameters
Following minGPT: This long function is unfortunately doing something very simple and is being very defensive: We are sepa
image_synthesis/modeling/transformers/transformer_utils.py:365
↓ 2 callersFunctionpatch_device
(module)
image_synthesis/modeling/modules/clip/clip.py:123
↓ 2 callersFunctionpatch_float
(module)
image_synthesis/modeling/modules/clip/clip.py:143
↓ 2 callersMethodprepare_content
(self, batch, with_mask=False)
image_synthesis/modeling/models/unconditional_dalle.py:55
↓ 2 callersMethodprepare_content
(self, batch, with_mask=False)
image_synthesis/modeling/models/conditional_dalle.py:68
↓ 2 callersMethodprepare_content
(self, batch, with_mask=False)
image_synthesis/modeling/models/dalle.py:72
↓ 2 callersMethodq_sample
(self, log_x_start, t)
image_synthesis/modeling/transformers/diffusion_transformer.py:264
↓ 2 callersMethodq_sample
(self, log_x_start, t)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:269
↓ 2 callersFunctionreduce_dict
(input_dict, average=True)
image_synthesis/distributed/distributed.py:114
↓ 2 callersFunctionremove_prefix
(text, prefix)
image_synthesis/data/utils/manage.py:108
↓ 2 callersMethodresume
(self, path=None, # The path of last.pth load_optimizer_and_scheduler=True, # w
image_synthesis/engine/solver.py:350
↓ 2 callersMethodsample
( self, batch, clip = None, temperature = 1., return_rec = True,
image_synthesis/modeling/models/dalle.py:223
↓ 2 callersMethodshared_step
(self, batch, batch_idx)
image_synthesis/taming/models/cond_transformer.py:283
↓ 2 callersMethodstep
(self, batch, phase='train')
image_synthesis/engine/solver.py:230
↓ 2 callersMethodtop_k_logits
(self, logits, k)
image_synthesis/taming/models/cond_transformer.py:106
↓ 1 callersMethodLoadModel
(self, config_path, ckpt_path)
image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:82
↓ 1 callersMethodLoadModel
(self, config_path, ckpt_path)
image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:164
↓ 1 callersMethodLoadModel
(self, config_path, ckpt_path)
image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:242
↓ 1 callersMethod__init__
(self)
image_synthesis/taming/modules/losses/vqperceptual.py:10
↓ 1 callersMethod__init__
(self, ddconfig, lossconfig, n_embed, embe
image_synthesis/taming/models/vqgan.py:13
↓ 1 callersMethod__len__
(self)
image_synthesis/data/imagenet_dataset.py:36
↓ 1 callersMethod_get_optimizer_and_scheduler
(self, op_sc_list)
image_synthesis/engine/solver.py:112
↓ 1 callersMethod_increase_lr
(self, epoch)
image_synthesis/engine/lr_scheduler.py:155
↓ 1 callersMethod_increase_lr
(self, epoch)
image_synthesis/engine/lr_scheduler.py:258
↓ 1 callersMethod_prepare_for_warmup
(self)
image_synthesis/engine/lr_scheduler.py:96
↓ 1 callersMethod_reduce_lr
(self, epoch)
image_synthesis/engine/lr_scheduler.py:145
↓ 1 callersMethod_reduce_lr
(self, epoch)
image_synthesis/engine/lr_scheduler.py:247
↓ 1 callersMethod_reset
Resets num_bad_epochs counter and cooldown counter.
image_synthesis/engine/lr_scheduler.py:113
↓ 1 callersMethod_train_loss
(self, x, cond_emb, is_train=True)
image_synthesis/modeling/transformers/diffusion_transformer.py:294
↓ 1 callersMethod_train_loss
(self, x, cond_emb, is_train=True)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:299
↓ 1 callersMethodadd_images
Log a scalar variable.
image_synthesis/engine/logger.py:78
↓ 1 callersFunctionalpha_schedule
(time_step, N=100, att_1 = 0.99999, att_T = 0.000009, ctt_1 = 0.000009, ctt_T = 0.99999)
image_synthesis/modeling/transformers/diffusion_transformer.py:53
↓ 1 callersFunctionalpha_schedule
(time_step, N=100, att_1 = 0.99999, att_T = 0.000009, ctt_1 = 0.000009, ctt_T = 0.99999)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:46
↓ 1 callersMethodattention
(self, x: torch.Tensor)
image_synthesis/modeling/modules/clip/model.py:180
↓ 1 callersFunctionavailable_models
Returns the names of available CLIP models
image_synthesis/modeling/modules/clip/clip.py:67
↓ 1 callersFunctionbasic_clean
(text)
image_synthesis/modeling/modules/clip/simple_tokenizer.py:50
↓ 1 callersFunctionbasic_clean
(text)
image_synthesis/modeling/modules/clip/clip_tokenizer.py:50
↓ 1 callersMethodbpe
(self, token)
image_synthesis/modeling/modules/clip/simple_tokenizer.py:84
↓ 1 callersMethodbpe
(self, token)
image_synthesis/modeling/modules/clip/clip_tokenizer.py:84
↓ 1 callersMethodbuild_attention_mask
(self)
image_synthesis/modeling/modules/clip/model.py:323
↓ 1 callersFunctionbuild_dataloader
(config, args=None, return_dataset=False)
image_synthesis/data/build.py:7
↓ 1 callersFunctionbuild_model
(state_dict: dict)
image_synthesis/modeling/modules/clip/model.py:397
↓ 1 callersMethodcalculate_adaptive_weight
(self, nll_loss, g_loss, last_layer=None)
image_synthesis/taming/modules/losses/vqperceptual.py:63
↓ 1 callersFunctionconvert_weights
Convert applicable model parameters to fp16
image_synthesis/modeling/modules/clip/model.py:373
↓ 1 callersMethodcreate
(file,keys,values)
image_synthesis/data/utils/manage.py:263
↓ 1 callersMethoddecode
(self, tokens)
image_synthesis/modeling/modules/clip/simple_tokenizer.py:133
↓ 1 callersFunctiondefault_bpe
()
image_synthesis/modeling/modules/clip/simple_tokenizer.py:11
↓ 1 callersFunctiondefault_bpe
()
image_synthesis/modeling/modules/clip/clip_tokenizer.py:11
↓ 1 callersMethoddeinitialze
(self)
image_synthesis/data/utils/manage.py:131
↓ 1 callersFunctiondownload
(url, local_path, chunk_size=1024)
image_synthesis/taming/util.py:18
↓ 1 callersMethodencode
(self, text)
image_synthesis/modeling/modules/clip/clip_tokenizer.py:125
↓ 1 callersMethodencode_image
(self, image)
image_synthesis/modeling/modules/clip/model.py:338
↓ 1 callersMethodencode_text
(self, text)
image_synthesis/modeling/embeddings/clip_text_embedding.py:46
↓ 1 callersMethodencode_text
(self, text)
image_synthesis/modeling/modules/clip/model.py:341
↓ 1 callersFunctionfind_free_port
()
image_synthesis/distributed/launch.py:10
↓ 1 callersFunctionformat_dict
(d)
image_synthesis/utils/misc.py:92
↓ 1 callersFunctionformat_number
(num)
image_synthesis/utils/misc.py:74
↓ 1 callersMethodforward
(self, image, text)
image_synthesis/modeling/modules/clip/model.py:356
↓ 1 callersFunctionfunc_wrapper
(func)
image_synthesis/data/utils/manage.py:17
↓ 1 callersFunctionget_args
()
train.py:28
↓ 1 callersMethodget_model
(self, ema, model_path, config_path)
inference_VQ_Diffusion.py:34
↓ 1 callersMethodinference_generate_sample_with_class
(self, text, truncation_rate, save_root, batch_size,fast=False)
inference_VQ_Diffusion.py:66
↓ 1 callersMethodinit_cond_stage_from_ckpt
(self, config)
image_synthesis/taming/models/cond_transformer.py:64
↓ 1 callersMethodinit_first_stage_from_ckpt
(self, config)
image_synthesis/taming/models/cond_transformer.py:58
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list())
image_synthesis/taming/models/cond_transformer.py:48
↓ 1 callersMethodinitialize
(self,close=True)
image_synthesis/data/utils/manage.py:136
↓ 1 callersMethodinitialize
(self)
image_synthesis/data/utils/manage.py:231
↓ 1 callersMethodinitialize
(self)
image_synthesis/data/utils/manage.py:303
↓ 1 callersMethodinitialize_parameters
(self)
image_synthesis/modeling/modules/clip/model.py:294
↓ 1 callersMethodis_better
(self, a, best)
image_synthesis/engine/lr_scheduler.py:169
↓ 1 callersFunctionlaunch
(fn, n_gpu_per_machine, n_machine=1, machine_rank=0, dist_url=None, args=())
image_synthesis/distributed/launch.py:22
↓ 1 callersMethodload_from_pretrained
(self, name="vgg_lpips")
image_synthesis/taming/modules/losses/lpips.py:27
↓ 1 callersFunctionload_img
(filepath)
image_synthesis/data/cub200_dataset.py:12
↓ 1 callersFunctionload_img
(filepath)
image_synthesis/data/imagenet_dataset.py:10
↓ 1 callersFunctionload_img
(filepath)
image_synthesis/data/mscoco_dataset.py:10
↓ 1 callersMethodload_img
(self, index)
image_synthesis/data/imagenet_dataset.py:45
↓ 1 callersFunctionlog_categorical
(log_x_start, log_prob)
image_synthesis/modeling/transformers/diffusion_transformer.py:38
↓ 1 callersFunctionlog_categorical
(log_x_start, log_prob)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:31
↓ 1 callersFunctionmain
()
train.py:106
↓ 1 callersFunctionmerge_opts_to_config
(config, opts)
image_synthesis/utils/misc.py:33
↓ 1 callersFunctionmodify_config_for_debug
(config)
image_synthesis/utils/misc.py:50
↓ 1 callersFunctionmodify_dict
(c, nl, v)
image_synthesis/utils/misc.py:34
↓ 1 callersMethodmodify_to_inference
(self)
image_synthesis/engine/ema.py:46
↓ 1 callersMethodmodify_to_train
(self)
image_synthesis/engine/ema.py:61
↓ 1 callersFunctionmortonify
(i,j) index to linear morton code
image_synthesis/taming/modules/transformer/permuter.py:47
↓ 1 callersFunctionnorm
(path)
image_synthesis/data/utils/manage.py:58
↓ 1 callersMethodp_pred
(self, log_x, cond_emb, t)
image_synthesis/modeling/transformers/diffusion_transformer.py:240
↓ 1 callersMethodp_pred
(self, log_x, cond_emb, t)
image_synthesis/modeling/transformers/diffusion_transformer_amp.py:245
↓ 1 callersMethodp_sample_with_truncation
(self, func, sample_type)
image_synthesis/modeling/models/dalle.py:95
↓ 1 callersMethodpostprocess
imgs: B x C x H x W, in the range 0-1
image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:105
↓ 1 callersMethodpostprocess
imgs: B x C x H x W, in the range 0-1
image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:184
↓ 1 callersMethodpostprocess
imgs: B x C x H x W, in the range 0-1
image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:262
↓ 1 callersMethodpredict_start_with_truncation
(self, func, sample_type)
image_synthesis/modeling/models/unconditional_dalle.py:76
↓ 1 callersMethodpredict_start_with_truncation
(self, func, sample_type)
image_synthesis/modeling/models/conditional_dalle.py:90
↓ 1 callersMethodpredict_start_with_truncation
(self, func, sample_type)
image_synthesis/modeling/models/dalle.py:106
↓ 1 callersMethodprepare_input
(self, batch)
image_synthesis/modeling/models/unconditional_dalle.py:72
↓ 1 callersMethodprepare_input
(self, batch)
image_synthesis/modeling/models/conditional_dalle.py:85
↓ 1 callersMethodprepare_input
(self, batch)
image_synthesis/modeling/models/dalle.py:90
↓ 1 callersMethodpreprocess
imgs: B x C x H x W, in the range 0-255
image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:97
↓ 1 callersMethodpreprocess
imgs: B x C x H x W, in the range 0-255
image_synthesis/modeling/codecs/image_codec/taming_gumbel_vqvae.py:176
← previousnext →101–200 of 543, ranked by callers