MCPcopy Create free account

hub / github.com/ThisisBillhe/NAR / functions

Functions683 in github.com/ThisisBillhe/NAR

⨍ Functions 683◇ Types & classes 116
↓ 1 callersMethodevaluate
(self, no_fvd=False)
NAR-videos/eval/rfvd_evaluator.py:89
↓ 1 callersMethodevaluate_epoch
(self)
NAR-videos/trainers/base_trainer.py:666
↓ 1 callersFunctionevaluate_model
(opt)
NAR-images/evaluations/t2i/evaluation.py:207
↓ 1 callersMethodevaluate_step
(self, data)
NAR-videos/trainers/base_trainer.py:660
↓ 1 callersFunctionexists
(val)
NAR-images/tokenizer/tokenizer_image/discriminator.py:254
↓ 1 callersFunctionexists
(val)
NAR-images/tokenizer/tokenizer_image/discriminator_stylegan.py:100
↓ 1 callersFunctionfid_inception_v3
Build pretrained Inception model for FID computation The Inception model for FID computation uses a different set of weights and has a slight
NAR-videos/utils/fid/inception.py:196
↓ 1 callersFunctionfid_scaling_law_cfg
()
NAR-images/tools/draw_figure.py:43
↓ 1 callersFunctionfid_scaling_law_no_cfg
()
NAR-images/tools/draw_figure.py:6
↓ 1 callersMethodforward
(self, x)
NAR-videos/models/embed.py:85
↓ 1 callersMethodforward_ar_model
(self, z, c)
NAR-videos/trainers/larp_ar_fp_trainer.py:198
↓ 1 callersMethodforward_ar_model
(self, z, c)
NAR-videos/trainers/larp_ar_trainer.py:165
↓ 1 callersMethodgen_fn
()
NAR-images/evaluations/c2i/evaluator.py:459
↓ 1 callersFunctiongenerate_position
(c, latent_shape, cond_len)
NAR-videos/ar/generate.py:112
↓ 1 callersFunctiongenerate_shard_index
Generate a shard index JSON file for the given directory.
NAR-images/scripts/analyze_tar.py:19
↓ 1 callersFunctionget_2d_sincos_pos_embed
grid_size: int of the grid height and width return: pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim] (w/
NAR-videos/models/embed.py:283
↓ 1 callersFunctionget_2d_sincos_pos_embed_from_grid
(embed_dim, grid)
NAR-videos/models/embed.py:301
↓ 1 callersFunctionget_args
()
NAR-videos/eval/eval_larp_tokenizer.py:14
↓ 1 callersFunctionget_args
()
NAR-videos/eval/calc_fvd_from_multiple_feature_stats.py:13
↓ 1 callersFunctionget_calculating_flag_file_path
( ar_model_id, num_samples=None, cfg_scale=None, )
NAR-videos/sample_one.py:27
↓ 1 callersFunctionget_calculating_flag_file_path
( ar_model_id, num_samples=None, cfg_scale=None, )
NAR-videos/sample.py:27
↓ 1 callersMethodget_codebook_entry
(self, indices, shape)
NAR-images/tokenizer/vqgan/quantize.py:92
↓ 1 callersMethodget_codebook_entry
(self, indices, shape=None, channel_first=True)
NAR-images/tokenizer/tokenizer_image/vq_model.py:261
↓ 1 callersMethodget_codebook_entry
(self, indices, shape=None)
NAR-videos/models/bottleneck.py:327
↓ 1 callersMethodget_current_kl_weight
(self)
NAR-videos/trainers/larp_tokenizer_trainer.py:92
↓ 1 callersMethodget_emb
(self)
NAR-videos/models/bottleneck.py:253
↓ 1 callersMethodget_exp_name
(base_exp_name, cfg, args)
NAR-videos/trainers/base_trainer.py:165
↓ 1 callersMethodget_feature_stats_for_batch
(self, batch, feats=None, num_gpus=None)
NAR-videos/utils/fid/fid.py:78
↓ 1 callersMethodget_fsdp_wrap_module_list
(self)
NAR-images/autoregressive/models/gpt.py:449
↓ 1 callersMethodget_last_layer
(self)
NAR-videos/models/larp_tokenizer.py:324
↓ 1 callersMethodget_loss_q_weight
(self)
NAR-videos/trainers/larp_tokenizer_trainer.py:84
↓ 1 callersMethodget_sqt_weight
(self)
NAR-videos/trainers/larp_tokenizer_trainer.py:104
↓ 1 callersMethodget_video_batch_from_disk
(self, idx)
NAR-videos/datasets/video_dataset.py:314
↓ 1 callersMethodgetdata
(self, idx)
NAR-images/dataset/openimage.py:32
↓ 1 callersMethodindex_videos
(self)
NAR-videos/datasets/video_dataset.py:227
↓ 1 callersMethodinitialize_weights
(self)
NAR-images/autoregressive/models/gpt.py:308
↓ 1 callersMethodinitialize_weights
(self)
NAR-videos/models/loss.py:168
↓ 1 callersMethodinitialize_weights
(self)
NAR-videos/models/larp_ar.py:292
↓ 1 callersMethodinitialize_weights
(self)
NAR-videos/models/larp_tokenizer.py:243
↓ 1 callersMethodkl
(self)
NAR-videos/models/bottleneck.py:52
↓ 1 callersFunctionlecam_reg
Lecam loss for data-efficient and stable GAN training. Described in https://arxiv.org/abs/2104.03310 Args: real_pred: Predicti
NAR-videos/models/loss.py:17
↓ 1 callersMethodless_thans
(self, batch_1, radii_1, batch_2, radii_2)
NAR-images/evaluations/c2i/evaluator.py:418
↓ 1 callersMethodload_dataset
(self)
NAR-images/evaluations/t2i/evaluation.py:82
↓ 1 callersMethodload_from_pretrained
(self, name="vgg_lpips")
NAR-images/tokenizer/tokenizer_image/lpips.py:69
↓ 1 callersFunctionload_model
(args)
NAR-images/tools/push_vae_to_hf.py:17
↓ 1 callersMethodlogits_to_token_embedding_with_ss
(self, logits, ar_input_staring_from_idx_1, mask=None, **kwargs)
NAR-videos/models/larp_tokenizer.py:515
↓ 1 callersFunctionmain
(args)
NAR-images/tools/push_gpt_to_hf.py:13
↓ 1 callersFunctionmain
(args)
NAR-images/tools/check_image_codes.py:9
↓ 1 callersFunctionmain
(args)
NAR-images/tools/openimage_json.py:44
↓ 1 callersFunctionmain
()
NAR-images/evaluations/c2i/evaluator.py:31
↓ 1 callersFunctionmain
Trains a new DiT model.
NAR-images/language/extract_t5_feature.py:53
↓ 1 callersFunctionmain
(args)
NAR-images/tokenizer/vae/sd_vae_demo.py:9
↓ 1 callersFunctionmain
(args)
NAR-images/tokenizer/vae/reconstruction_vae_ddp.py:81
↓ 1 callersFunctionmain
(args)
NAR-images/tokenizer/vqgan/reconstruction_vqgan_ddp.py:83
↓ 1 callersFunctionmain
(args)
NAR-images/tokenizer/vqgan/taming_vqgan_demo.py:17
↓ 1 callersFunctionmain
(args)
NAR-images/tokenizer/validation/val_ddp.py:76
↓ 1 callersFunctionmain
(args)
NAR-images/tokenizer/tokenizer_image/reconstruction_vq_ddp.py:43
↓ 1 callersFunctionmain
(args)
NAR-images/tokenizer/tokenizer_image/vq_demo.py:13
↓ 1 callersFunctionmain
Trains a new model.
NAR-images/tokenizer/tokenizer_image/vq_train.py:36
↓ 1 callersFunctionmain
(args)
NAR-images/tokenizer/consistencydecoder/reconstruction_cd_ddp.py:81
↓ 1 callersFunctionmain
(args)
NAR-images/tokenizer/consistencydecoder/cd_demo.py:9
↓ 1 callersFunctionmain
(args)
NAR-images/autoregressive/sample/sample_t2i.py:24
↓ 1 callersFunctionmain
(args)
NAR-images/autoregressive/sample/sample_c2i_ddp.py:40
↓ 1 callersFunctionmain
(args)
NAR-images/autoregressive/sample/sample_c2i.py:20
↓ 1 callersFunctionmain
(args)
NAR-images/autoregressive/sample/sample_t2i_ddp.py:26
↓ 1 callersFunctionmain
(args)
NAR-images/autoregressive/train/extract_codes_c2i.py:26
↓ 1 callersFunctionmain
(args)
NAR-images/autoregressive/train/train_c2i_fsdp.py:104
↓ 1 callersFunctionmain
(args)
NAR-images/autoregressive/train/train_c2i.py:59
↓ 1 callersFunctionmain
(args)
NAR-images/autoregressive/train/train_t2i_webdata.py:60
↓ 1 callersFunctionmain
(args)
NAR-videos/sample_one.py:392
↓ 1 callersFunctionmain
()
NAR-videos/train.py:161
↓ 1 callersFunctionmain
(args)
NAR-videos/sample.py:405
↓ 1 callersFunctionmain
(args)
NAR-videos/eval/eval_larp_tokenizer.py:30
↓ 1 callersFunctionmain
(args)
NAR-videos/eval/calc_fvd_from_multiple_feature_stats.py:25
↓ 1 callersFunctionmain_worker
(rank, cfg)
NAR-videos/train.py:140
↓ 1 callersFunctionmake_cfg
(args)
NAR-videos/train.py:55
↓ 1 callersFunctionmake_dataset_train
(trainset_url, transform)
NAR-images/autoregressive/train/train_t2i_webdata.py:28
↓ 1 callersMethodmake_datasets
By default, train dataset performs shuffle and drop_last. Distributed sampler will extend the dataset with a prefix to make t
NAR-videos/trainers/base_trainer.py:299
↓ 1 callersMethodmode
(self)
NAR-videos/models/bottleneck.py:61
↓ 1 callersMethodmodify_model_before_compile_ddp
(self, model)
NAR-videos/trainers/base_trainer.py:424
↓ 1 callersMethodnatural_sort
(self, l)
NAR-images/evaluations/t2i/evaluation.py:77
↓ 1 callersFunctionnested_v
(dict, keys)
NAR-videos/train.py:100
↓ 1 callersFunctionopen_npz_array
(path: str, arr_name: str)
NAR-images/evaluations/c2i/evaluator.py:533
↓ 1 callersMethodothers_parameters
(self)
NAR-videos/models/larp_tokenizer.py:362
↓ 1 callersFunctionparse_args
(args=None)
NAR-videos/train.py:21
↓ 1 callersFunctionpredict_frames
( larp_ar_model: LARP_AR, larp_tokenizer: LARPTokenizer, output_dir: str, dataset_csv: str,
NAR-videos/sample_one.py:231
↓ 1 callersFunctionpredict_frames
( larp_ar_model: LARP_AR, larp_tokenizer: LARPTokenizer, output_dir: str, dataset_csv: str,
NAR-videos/sample.py:242
↓ 1 callersFunctionprefill
(model, cond_idx: torch.Tensor, input_pos: torch.Tensor, cfg_scale: float, **sampling_kwargs)
NAR-images/autoregressive/models/generate.py:75
↓ 1 callersFunctionprefill
(model, cond_idx: torch.Tensor, input_pos: torch.Tensor, cfg_scale: float, **sampling_kwargs)
NAR-videos/ar/generate.py:83
↓ 1 callersFunctionpreprocess
(video, resolution, sequence_length=None, in_channels=3, sample_every_n_frames=1)
NAR-videos/utils/fvd/fvd.py:215
↓ 1 callersMethodprior_ar_predict_n_rounds_ss
(self, ar_input, **kwargs)
NAR-videos/models/larp_tokenizer.py:545
↓ 1 callersMethodprocess_csv_data
(self, csv_file, cls_num, vid_num)
NAR-videos/datasets/video_dataset.py:187
↓ 1 callersMethodproject_in
(self, x)
NAR-videos/models/bottleneck.py:140
↓ 1 callersFunctionr1_gradient_penalty
(discriminator, real_video, penalty_cost=1.0)
NAR-videos/models/loss.py:37
↓ 1 callersFunctionrandom_crop_arr
(pil_image, image_size, min_crop_frac=0.8, max_crop_frac=1.0)
NAR-images/dataset/augmentation.py:29
↓ 1 callersMethodread_batch
(self, batch_size: int)
NAR-images/evaluations/c2i/evaluator.py:451
↓ 1 callersMethodread_batches
(self, batch_size: int)
NAR-images/evaluations/c2i/evaluator.py:458
↓ 1 callersFunctionread_video_with_retry
(uri, retries=5, delay=1)
NAR-videos/datasets/video_dataset.py:31
↓ 1 callersMethodremaining
(self)
NAR-images/evaluations/c2i/evaluator.py:455
↓ 1 callersMethodremap_to_used
(self, inds)
NAR-images/tokenizer/vqgan/quantize.py:144
← previousnext →201–300 of 683, ranked by callers