MCPcopy Create free account

hub / github.com/VITA-MLLM/VITA / functions

Functions1,650 in github.com/VITA-MLLM/VITA

⨍ Functions 1,650◇ Types & classes 320↳ Endpoints 1
↓ 1 callersFunctionsafe_save_model_for_hf_trainer
Collects the state dict and dump to disk.
vita/train/train.py:173
↓ 1 callersFunctionsave_error_files
(error_files, output_file_path)
data_tools/mmco_collect.py:16
↓ 1 callersFunctionsave_video
(images, video_filename)
web_demo/server.py:105
↓ 1 callersMethodsave_video_frames
(self, video, num_frames=8)
VLMEvalKit/vlmeval/dataset/videomme.py:149
↓ 1 callersMethodsave_video_frames
(self, imgs, video_name, frames)
VLMEvalKit/vlmeval/dataset/mvbench.py:496
↓ 1 callersFunctionselect_system_prompt
(current_request)
web_demo/server.py:644
↓ 1 callersMethodset_max_num
(self, dataset)
VLMEvalKit/vlmeval/vlm/mmalaya.py:325
↓ 1 callersMethodset_max_num
(self, dataset)
VLMEvalKit/vlmeval/vlm/vita/vita_qwen2.py:137
↓ 1 callersMethodset_max_num
(self, dataset)
VLMEvalKit/vlmeval/vlm/vita/vita_mistral.py:136
↓ 1 callersMethodset_max_num
(self, dataset)
VLMEvalKit/vlmeval/vlm/vita/vita.py:136
↓ 1 callersFunctionset_random_seed
(seed)
vita/train/train.py:24
↓ 1 callersFunctionset_random_seed
(seed)
data_tools/check_video_lost_fast.py:18
↓ 1 callersMethodset_system_role
( self, extra_inputs: Optional[dict] = None, )
vita/model/vita_tts/audioLLM.py:212
↓ 1 callersFunctionsetup
(app)
VLMEvalKit/docs/zh-CN/conf.py:241
↓ 1 callersMethodslow_fast
(self, image_features, sf_masks)
vita/model/vita_arch.py:285
↓ 1 callersMethodsplit_MUIR
(msgs)
VLMEvalKit/vlmeval/dataset/image_mcq.py:313
↓ 1 callersFunctionsplit_chessboard
x: b * c * h * w Deividing x into num_split**2 sub-squares, and concatenate all the sub-squares on the batch dimension
vita/util/s2wrapper/utils.py:11
↓ 1 callersFunctionsplit_file_into_four
(input_file)
data_tools/cut_txt.py:1
↓ 1 callersFunctionsplit_into_sentences
(text)
web_demo/web_ability_demo.py:145
↓ 1 callersFunctionsplit_model
(model_name)
VLMEvalKit/vlmeval/vlm/mmalaya.py:161
↓ 1 callersFunctionsplit_model
(model_name)
VLMEvalKit/vlmeval/vlm/internvl_chat.py:100
↓ 1 callersMethodsplit_subtitle
(self, data)
VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:364
↓ 1 callersFunctionsplit_to_even_chunks
Split a list of indices into `chunks` chunks of roughly equal lengths.
vita/train/vita_trainer.py:40
↓ 1 callersFunctionstream_results
(results_generator)
web_demo/server.py:317
↓ 1 callersFunctiontimestr
(second=True, minute=False)
VLMEvalKit/vlmeval/smp/misc.py:129
↓ 1 callersFunctiontokenizer_image_audio_token
(prompt, tokenizer, image_token_index=IMAGE_TOKEN_INDEX, audio_token_index=AUDIO_TOKEN_INDEX, return_tensors=N
web_demo/server.py:120
↓ 1 callersFunctiontrain
()
vita/train/train.py:212
↓ 1 callersFunctiontsv_unescape
Unescape strings in the TSV file. Escaped characters include: newline (0x10) -> backslash + n vertical bar (0x7C) -> backslash + p
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:476
↓ 1 callersFunctionunwrap_hf_pkl
(pth, suffix='.mp4')
VLMEvalKit/vlmeval/dataset/mmbench_video.py:11
↓ 1 callersMethoduse_cot
(self, dataset=None)
VLMEvalKit/vlmeval/vlm/minicpm_v.py:298
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/mmalaya.py:254
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/transcore_m.py:83
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/internvl_chat.py:179
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/omnilmm.py:146
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/parrot.py:61
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/minicpm_v.py:30
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/omchat.py:44
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/rbdash.py:194
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/mplug_owl3.py:37
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/wemm.py:17
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/mantis.py:92
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/cogvlm.py:73
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/mplug_owl2.py:41
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/vita/vita_qwen2.py:49
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/vita/vita_mistral.py:49
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/vita/vita.py:49
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer.py:115
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2_4KHD.py:183
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/xcomposer/sharecaptioner.py:22
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2.py:162
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2d5.py:225
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/llava/llava.py:69
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/llava/llava.py:261
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/vlm/llava/llava_xtuner.py:156
↓ 1 callersMethoduse_custom_prompt
(self, dataset)
VLMEvalKit/vlmeval/api/sensechat_vision.py:83
↓ 1 callersMethoduse_upsize
(self, dataset=None)
VLMEvalKit/vlmeval/vlm/minicpm_v.py:309
↓ 1 callersMethodutterance_cmvn
( x: np.ndarray, input_length: int, normalize_means: Optional[bool] = True, no
web_demo/vllm_tools/qwen2p5_model_weight_file/processor_whale.py:210
↓ 1 callersFunctionvideo2patches
(patch_images, data_args, processor)
vita/util/data_utils_video_patch_audio.py:671
↓ 1 callersFunctionwrap_question_for_omni_lmm
(question, image_token_len, tokenizer)
VLMEvalKit/vlmeval/vlm/omnilmm.py:73
FunctionLLaVABench_atomeval
(model, prompt)
VLMEvalKit/vlmeval/dataset/utils/llavabench.py:49
FunctionMATH_V_auxeval
(model, line)
VLMEvalKit/vlmeval/dataset/utils/mathv.py:123
FunctionMMVet_auxeval
(model, line)
VLMEvalKit/vlmeval/dataset/utils/mmvet.py:45
FunctionMathVista_auxeval
(model, line)
VLMEvalKit/vlmeval/dataset/utils/mathvista.py:104
FunctionOCRBench_eval
(eval_file)
VLMEvalKit/vlmeval/dataset/utils/ocrbench.py:4
FunctionYOrN_auxeval
(model, line)
VLMEvalKit/vlmeval/dataset/utils/yorn.py:195
Method__call__
(self, item)
vita/model/multimodal_encoder/eva_clip/eva_clip_processors.py:18
Method__call__
(self, item)
vita/model/multimodal_encoder/eva_clip/eva_clip_processors.py:64
Method__call__
(self, instances: Sequence[Dict])
vita/util/data_utils_video_audio_patch.py:1253
Method__call__
(self, instances: Sequence[Dict])
vita/util/data_utils_video_audio_neg_patch.py:1395
Method__call__
(self, instances: Sequence[Dict])
vita/util/data_utils_video_audio_neg_patch_fo.py:1395
Method__call__
(self, instances: Sequence[Dict])
vita/util/data_utils_video_patch_audio.py:1303
Method__call__
(self, instances: Sequence[Dict])
vita/util/data_utils_video_audio_neg_frameCat.py:1132
Method__call__
(self, instances: Sequence[Dict])
vita/util/data_utils_video_audio.py:759
Method__call__
(self, output_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs)
vita/util/mm_utils.py:151
Method__call__
(self, instances: Sequence[Dict])
vita/util/data_utils_video_audio_patch_sf.py:1259
Method__call__
(self, inputs)
VLMEvalKit/vlmeval/utils/mp_util.py:19
Method__call__
(self, img_group)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:57
Method__call__
(self, img_group)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:85
Method__call__
(self, img_group)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:110
Method__call__
(self, img_group, is_flow=False)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:121
Method__call__
(self, tensor)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:139
Method__call__
(self, img_group)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:162
Method__call__
(self, img_group)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:177
Method__call__
(self, img_group)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:218
Method__call__
(self, img_group)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:266
Method__call__
(self, img_group)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:353
Method__call__
(self, images)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:395
Method__call__
(self, img_group)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:410
Method__call__
(self, pic)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:431
Method__call__
(self, data)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:449
Method__call__
(self, input_ids: torch.LongTensor, scores: torch.FloatTensor)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer.py:15
Method__call__
(self, input_ids: torch.LongTensor, scores: torch.FloatTensor)
VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:52
Method__call__
Main method to featurize and prepare for the model one or several sequence(s). Args: raw_speech (`np.ndarray`, `List[flo
web_demo/vllm_tools/qwen2p5_model_weight_file/processor_whale.py:252
Method__call__
x: torch.Tensor audio chunk (see examples in repo) return_seconds: bool (default - False) whether return tim
web_demo/wakeup_and_vad/wakeup_and_vad.py:61
Method__eq__
(self, other)
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:267
Method__eq__
(self, other)
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:301
Method__eq__
(self, other)
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:363
Method__getattr__
(self, attr)
vita/util/utils.py:79
Method__getitem__
(self, i)
vita/util/data_utils_video_audio_patch.py:740
Method__getitem__
(self, i)
vita/util/data_utils_video_audio_neg_patch.py:882
← previousnext →701–800 of 1,650, ranked by callers