Functions — github.com/bytedance/Shot2Story

hub / github.com/bytedance/Shot2Story / functions

Functions1,483 in github.com/bytedance/Shot2Story

⨍ Functions 1,483◇ Types & classes 348↳ Endpoints 10

↓ 1 callersMethod_rampup_factor

(self, epoch, iters, num_iters_per_epoch)

code/lavis/models/albef_models/albef_pretrain.py:102

↓ 1 callersMethod_rampup_factor

(self, epoch, iters, num_iters_per_epoch)

code/lavis/models/albef_models/albef_retrieval.py:104

↓ 1 callersMethod_rank_answers

Generate the first token of answers using decoder and select ${num_ans_candidates} most probable ones. Then select answers from answe

code/lavis/models/blip_models/blip_vqa.py:277

↓ 1 callersMethod_relative_position_bucket

Adapted from Mesh Tensorflow: https://github.com/tensorflow/mesh/blob/0cb87fe07da627bf0b7e60475d59f95ed6b5be3d/mesh_tensorflow/transf

code/lavis/models/blip2_models/modeling_t5.py:393

↓ 1 callersMethod_reload_best_model

Load the best checkpoint for evaluation.

code/lavis/runners/runner_base.py:660

↓ 1 callersMethod_report_metrics

(scores_i2t, scores_t2i, txt2img, img2txt)

code/lavis/tasks/retrieval.py:54

↓ 1 callersMethod_report_metrics

(self, eval_result_file, split_name)

code/lavis/tasks/captioning_custom.py:87

↓ 1 callersMethod_report_metrics

(self, eval_result_file, split_name)

code/lavis/tasks/multimodal_classification.py:66

↓ 1 callersMethod_report_metrics

(self, eval_result_file, split_name)

code/lavis/tasks/video_text_pretrain.py:189

↓ 1 callersMethod_report_metrics

TODO: add other evaluation metrics for GQA

code/lavis/tasks/vqa_reading_comprehension.py:193

↓ 1 callersMethod_report_metrics

Use official VQA evaluation script to report metrics.

code/lavis/tasks/vqa.py:130

↓ 1 callersMethod_report_metrics

(self, eval_result_file, split_name)

code/lavis/tasks/captioning.py:83

↓ 1 callersMethod_save_result_leaderboard

Saving the results in the format required for leaderboard evaluation.

code/lavis/tasks/vqa_reading_comprehension.py:232

↓ 1 callersMethodafter_evaluation

(self, val_result, split_name, **kwargs)

code/lavis/tasks/vqa.py:117

↓ 1 callersMethodanswer

(self, conv, num_captions=1, max_new_tokens=300, num_beams=1, min_length=1, top_p=0.9, repetiti

code/lavis/conversation/conversation.py:509

↓ 1 callersMethodanswer_extraction

(self, caption, num_question_generation=30)

code/lavis/models/img2prompt_models/img2prompt_vqa.py:252

↓ 1 callersMethodanswer_text

(self, conv, num_captions=1, max_new_tokens=300, num_beams=1, min_length=1, top_p=0.9, repetiti

code/lavis/conversation/conversation.py:551

↓ 1 callersFunctionapply_rotary_pos_emb

(q, k, cos, sin, position_ids)

code/lavis/models/blip2_models/modeling_llama.py:133

↓ 1 callersFunctionapply_to_sample

(f, sample)

code/lavis/datasets/data_utils.py:116

↓ 1 callersFunctionbasic_clean

(text)

code/lavis/models/clip_models/tokenizer.py:70

↓ 1 callersMethodbefore_evaluation

(self, model, dataset, **kwargs)

code/lavis/tasks/base_task.py:75

↓ 1 callersMethodbpe

(self, token)

code/lavis/models/clip_models/tokenizer.py:111

↓ 1 callersMethodbuild

Create by split datasets inheriting torch.utils.data.Datasets. # build() can be dataset-specific. Overwrite to customize.

code/lavis/datasets/builders/base_dataset_builder.py:244

↓ 1 callersMethodbuild_attention_mask

(self)

code/lavis/models/clip_models/model.py:538

↓ 1 callersMethodbuild_dataset_config

(config)

code/lavis/common/config.py:88

↓ 1 callersMethodbuild_datasets

(self)

code/lavis/datasets/builders/base_dataset_builder.py:44

↓ 1 callersMethodbuild_model_config

(config, **kwargs)

code/lavis/common/config.py:57

↓ 1 callersFunctionbuild_rotary_pos_embed

NOTE: shape arg should include spatial dim only

code/lavis/models/clip_models/timm_model.py:449

↓ 1 callersMethodbuild_runner_config

(config)

code/lavis/common/config.py:84

↓ 1 callersFunctioncoco_caption_eval

(coco_gt_root, results_file, split)

code/lavis/tasks/captioning.py:109

↓ 1 callersFunctioncoco_dialogue_eval

(coco_gt_root, results_file, split)

code/lavis/tasks/dialogue.py:93

↓ 1 callersMethodcollater

(self, samples)

code/lavis/datasets/datasets/base_dataset.py:37

↓ 1 callersMethodcompute_bias

Compute binned relative position bias

code/lavis/models/blip2_models/modeling_t5.py:447

↓ 1 callersMethodcompute_color_histograms

(frames)

code/transnetv2_pytorch.py:276

↓ 1 callersFunctioncompute_gradcam_batch

(model, visual_input, text_input, tokenized_text, block_num=6)

code/app/multimodal_search.py:191

↓ 1 callersFunctioncompute_sim_matrix

(model, data_loader, **kwargs)

code/lavis/models/blip2_models/blip2.py:205

↓ 1 callersMethodcompute_sim_matrix

(self, data_loader, **kwargs)

code/lavis/models/clip_models/model.py:720

↓ 1 callersMethodcompute_vtm

( self, text_embeds, text_atts, image_embeds, image_atts, sim_i2t, sim_t2i )

code/lavis/models/alpro_models/alpro_retrieval.py:150

↓ 1 callersFunctionconv2d_same

( x, weight: torch.Tensor, bias: Optional[torch.Tensor] = None, stride: Tuple[int, int] = (1,

code/lavis/models/timesformer/conv2d_same.py:66

↓ 1 callersFunctioncosine_lr_schedule

Decay the learning rate

code/lavis/common/optims.py:97

↓ 1 callersFunctioncreate_clip_vit_L

(img_size=224,use_checkpoint=False,precision="fp16")

code/lavis/models/clip_vit.py:233

↓ 1 callersMethodcreate_context_prompt

(self, samples, num_caps_per_img=30)

code/lavis/models/img2prompt_models/img2prompt_vqa.py:349

↓ 1 callersFunctioncreate_eva_vit_g

(img_size=224,drop_path_rate=0.4,use_checkpoint=False,precision="fp16")

code/lavis/models/eva_vit.py:415

↓ 1 callersFunctioncreate_runner_config_validator

()

code/lavis/common/config.py:261

↓ 1 callersMethodcreate_task_prompt

( self, samples, question_type="neural", num_question_per_img=30 )

code/lavis/models/img2prompt_models/img2prompt_vqa.py:368

↓ 1 callersFunctiondefault_bpe

()

code/lavis/models/clip_models/tokenizer.py:25

↓ 1 callersMethoddefault_config_path

(cls, type="default")

code/lavis/datasets/builders/base_dataset_builder.py:87

↓ 1 callersFunctiondf_from_shelve

(chunk_size, func, dataset_name)

code/lavis/datasets/download_scripts/DownloadConceptualCaptions/download_data_cc3m.py:184

↓ 1 callersFunctiondf_from_shelve

(chunk_size, func, dataset_name)

code/lavis/datasets/download_scripts/DownloadConceptualCaptions/download_data_cc12m.py:184

↓ 1 callersFunctiondf_multiprocess

(df, processes, chunk_size, func, dataset_name)

code/lavis/datasets/download_scripts/DownloadConceptualCaptions/download_data_cc3m.py:40

↓ 1 callersFunctiondf_multiprocess

(df, processes, chunk_size, func, dataset_name)

code/lavis/datasets/download_scripts/DownloadConceptualCaptions/download_data_cc12m.py:40

↓ 1 callersMethoddispl_item

(self, index)

code/lavis/datasets/datasets/gqa_datasets.py:19

↓ 1 callersFunctiondownload_datasets

Download the Imagenet-R dataset archives and expand them in the folder provided as parameter

code/lavis/datasets/download_scripts/download_msrvtt.py:38

↓ 1 callersFunctiondownload_datasets

(root, url)

code/lavis/datasets/download_scripts/download_coco.py:29

↓ 1 callersFunctiondownload_datasets

(root, url)

code/lavis/datasets/download_scripts/download_gqa.py:24

↓ 1 callersFunctiondownload_datasets

(root, url)

code/lavis/datasets/download_scripts/download_vg.py:27

↓ 1 callersFunctiondownload_datasets

Download the Imagenet-R dataset archives and expand them in the folder provided as parameter

code/lavis/datasets/download_scripts/download_didemo.py:23

↓ 1 callersFunctiondownload_datasets

(root, url)

code/lavis/datasets/download_scripts/download_msvd.py:24

↓ 1 callersMethodevaluate

(self, quesIds=None)

code/lavis/common/vqa_tools/vqa_eval.py:193

↓ 1 callersFunctionevaluate_input_shots

(input_text, fps, total_frames)

code/lavis/conversation/conversation.py:274

↓ 1 callersFunctionevaluate_shot_detection

(total_frames, shot_list, fps)

code/lavis/conversation/conversation.py:303

↓ 1 callersMethodevaluation

(self, model, data_loader, cuda_enabled=True)

code/lavis/tasks/base_task.py:84

↓ 1 callersFunctionextract_archive

Extract archive. Args: from_path: the path of the archive. to_path: the root path of the extracted files (directory of from_path)

code/lavis/datasets/data_utils.py:255

↓ 1 callersFunctionfetch_requirements

(filename)

code/setup.py:16

↓ 1 callersFunctionfetch_single_image

(image_url, timeout=None, retries=0)

code/lavis/datasets/download_scripts/download_sbu.py:28

↓ 1 callersFunctionfind_scenes

(video_path: str, threshold=21.0)

code/lavis/conversation/conversation.py:161

↓ 1 callersMethodfix_init_weight

(self)

code/lavis/models/eva_vit.py:300

↓ 1 callersFunctionformat_text

(text)

code/app/dataset_browser.py:88

↓ 1 callersMethodforward

(self, x)

code/lavis/models/vit.py:45

↓ 1 callersMethodforward

Forward function for training and evaluation. Args: samples (dict): a dict of input samples, which contains the followin

code/lavis/models/blip_models/blip_nlvr.py:56

↓ 1 callersMethodforward

(self, samples, is_train=True)

code/lavis/models/blip_models/blip_classification.py:77

↓ 1 callersMethodforward

(self, samples, is_train=True)

code/lavis/models/albef_models/albef_classification.py:83

↓ 1 callersMethodforward

Forward function for training and evaluation. Args: samples (dict): a dict of input samples, which contains the followin

code/lavis/models/albef_models/albef_nlvr.py:79

↓ 1 callersMethodforward

( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = N

code/lavis/models/blip2_models/modeling_opt.py:843

↓ 1 callersMethodforward

(self, input_ids=None, attention_mask=None, **kwargs)

code/lavis/models/pnp_vqa_models/pnp_unifiedqav2_fid.py:79

↓ 1 callersMethodforward

(self, samples, is_train=True)

code/lavis/models/alpro_models/alpro_qa.py:53

↓ 1 callersMethodforward_cap

Args: samples (dict): A dictionary containing the following keys: - image (torch.Tensor): A tensor of shape (batc

code/lavis/models/img2prompt_models/img2prompt_vqa.py:138

↓ 1 callersMethodforward_decoder

(self, samples, image_embeds)

code/lavis/models/blip_models/blip_caption_video.py:67

↓ 1 callersMethodforward_decoder

(self, samples, encoder_out, **kwargs)

code/lavis/models/blip_models/blip_vqa.py:123

↓ 1 callersMethodforward_decoder

(self, samples, image_embeds)

code/lavis/models/blip_models/blip_caption.py:57

↓ 1 callersMethodforward_decoder

(self, samples, encoder_out, **kwargs)

code/lavis/models/albef_models/albef_vqa.py:167

↓ 1 callersMethodforward_features

(self, x)

code/lavis/models/eva_vit.py:324

↓ 1 callersMethodforward_features

(self, x)

code/lavis/models/timesformer/vit.py:411

↓ 1 callersMethodforward_image

(self, image)

code/lavis/models/blip2_models/blip2_qformer.py:323

↓ 1 callersMethodforward_itm

Args: samples (dict): A dictionary containing the following keys: - image (torch.Tensor): A tensor of shape (batc

code/lavis/models/img2prompt_models/img2prompt_vqa.py:68

↓ 1 callersMethodforward_qa_generation

(self, samples)

code/lavis/models/img2prompt_models/img2prompt_vqa.py:312

↓ 1 callersMethodfrom_other

(self, out_indices: Tuple[int])

code/lavis/models/timesformer/features.py:33

↓ 1 callersFunctiongather_features

( image_features, text_features, local_loss=False, gather_with_grad=False, rank=0, wor

code/lavis/models/clip_models/loss.py:20

↓ 1 callersFunctiongather_items

(samples, exclude=[])

code/app/dataset_browser.py:69

↓ 1 callersMethodgenerate

Args: samples (dict): A dictionary containing the following keys: - image (torch.Tensor): A tensor of shape (batc

code/lavis/models/blip_models/blip_caption.py:136

↓ 1 callersMethodgenerate

( self, samples, use_nucleus_sampling=False, num_beams=5, max_length=2

code/lavis/models/blip2_models/blip2_t5_instruct.py:280

↓ 1 callersMethodgenerate

Args: samples (dict): A dictionary containing the following keys: - image (torch.Tensor): A tensor of shape (batc

code/lavis/models/blip2_models/blip2_opt.py:165

↓ 1 callersMethodgenerate

( self, samples, use_nucleus_sampling=False, num_beams=5, max_length=2

code/lavis/models/blip2_models/blip2_vicuna_instruct.py:242

↓ 1 callersFunctiongenerate_caption

( model, image, use_nucleus_sampling=False, num_beams=3, max_length=40, min_length=5 )

code/app/caption.py:72

↓ 1 callersFunctiongetAttMap

(img, attMap, blur=True, overlap=True)

code/lavis/common/gradcam.py:7

↓ 1 callersFunctionget_asr

(asr_model, video_fn, fps, shot_list)

code/lavis/conversation/conversation.py:243

↓ 1 callersMethodget_attention_map

(self)

code/lavis/models/vit.py:85

↓ 1 callersMethodget_attention_map

(self)

code/lavis/models/blip_models/nlvr_encoder.py:137

↓ 1 callersMethodget_attn_gradients

(self)

code/lavis/models/vit.py:79

↓ 1 callersMethodget_attn_gradients

(self)

code/lavis/models/blip_models/nlvr_encoder.py:131

← previous next →301–400 of 1,483, ranked by callers