MCPcopy Create free account

hub / github.com/HumanMLLM/ViSpeak / functions

Functions1,447 in github.com/HumanMLLM/ViSpeak

⨍ Functions 1,447◇ Types & classes 292
↓ 1 callersMethod_post_decode
Decoding function, based on the posterior probability output, uses top_k, top_p, and temperature parameters for sampling. P
vispeak/model/vita_tts/audioLLM.py:339
↓ 1 callersFunction_process_digit_article
(inText)
VLMEvalKit/vlmeval/dataset/utils/vqa_eval.py:9
↓ 1 callersMethod_sample_crop_size
(self, im_size)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:281
↓ 1 callersMethod_sample_fix_offset
(self, image_w, image_h, crop_w, crop_h)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:310
↓ 1 callersMethod_save
(self, output_dir: Optional[str] = None, state_dict=None)
vispeak/train/vispeak_trainer.py:387
↓ 1 callersFunction_tasks_with_index
Add index to tasks.
VLMEvalKit/vlmeval/utils/mp_util.py:48
↓ 1 callersMethod_update_model_kwargs_for_generation
( self, outputs, model_kwargs, num_new_tokens: int = 1, )
vispeak/model/language_model/vispeak_qwen2.py:636
↓ 1 callersFunctionadd_encoder_args
Add Encoder common arguments.
vispeak/model/multimodal_encoder/whale/module/encoder/encoder.py:17
↓ 1 callersMethodadjust_kwargs
(self, dataset)
VLMEvalKit/vlmeval/vlm/qwen_vl.py:38
↓ 1 callersFunctionanls_compute
(groundtruth, prediction)
VLMEvalKit/vlmeval/dataset/utils/vqa_eval.py:230
↓ 1 callersMethodapply_prompt_template
(self, query)
VLMEvalKit/vlmeval/vlm/xgen_mm.py:36
↓ 1 callersFunctionbatched_forward
(model, x, batch_size=-1)
vispeak/util/s2wrapper/utils.py:55
↓ 1 callersFunctionbroadcat
(tensors, dim=-1)
vispeak/model/multimodal_encoder/eva_clip/eva_vit.py:26
↓ 1 callersMethodbuild_gen_config
(self, dataset)
VLMEvalKit/vlmeval/vlm/llava/llava_xtuner.py:140
↓ 1 callersMethodbuild_hallusionbench
(self, line)
VLMEvalKit/vlmeval/vlm/rbdash.py:211
↓ 1 callersMethodbuild_history
(self, message)
VLMEvalKit/vlmeval/vlm/internvl_chat.py:373
↓ 1 callersMethodbuild_history
(self, message)
VLMEvalKit/vlmeval/vlm/qwen_vl.py:90
↓ 1 callersFunctionbuild_mathv_gpt4_prompt
(line)
VLMEvalKit/vlmeval/dataset/utils/mathv.py:79
↓ 1 callersFunctionbuild_mathvista_gpt4_prompt
(line)
VLMEvalKit/vlmeval/dataset/utils/mathvista.py:53
↓ 1 callersMethodbuild_mcqa
(self, line)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2_4KHD.py:189
↓ 1 callersMethodbuild_mcqa
(self, line)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2.py:168
↓ 1 callersMethodbuild_mcqa
(self, line)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2d5.py:231
↓ 1 callersMethodbuild_mmbench
(self, line)
VLMEvalKit/vlmeval/vlm/rbdash.py:216
↓ 1 callersMethodbuild_mme
(self, line)
VLMEvalKit/vlmeval/vlm/rbdash.py:206
↓ 1 callersMethodbuild_mme_rw_prompt
(self, line, dataset_name)
VLMEvalKit/vlmeval/vlm/vispeak/vispeak_qwen2.py:117
↓ 1 callersFunctionbuild_mmlongbench_gpt4_prompt
(line)
VLMEvalKit/vlmeval/dataset/mmlongbench.py:76
↓ 1 callersMethodbuild_mmmu
(self, line)
VLMEvalKit/vlmeval/vlm/rbdash.py:234
↓ 1 callersFunctionbuild_mmvet_gpt4_prompt
(line)
VLMEvalKit/vlmeval/dataset/utils/mmvet.py:4
↓ 1 callersMethodbuild_msgs
(msgs_raw, system_prompt=None)
VLMEvalKit/vlmeval/api/qwen_api.py:44
↓ 1 callersMethodbuild_msgs
(msgs_raw)
VLMEvalKit/vlmeval/api/stepai.py:40
↓ 1 callersMethodbuild_msgs
(self, msgs_raw, system_prompt=None, dataset=None)
VLMEvalKit/vlmeval/api/glm_vision.py:49
↓ 1 callersMethodbuild_msgs_genai
(self, inputs)
VLMEvalKit/vlmeval/api/gemini.py:51
↓ 1 callersMethodbuild_msgs_vertex
(self, inputs)
VLMEvalKit/vlmeval/api/gemini.py:60
↓ 1 callersMethodbuild_multi_choice_prompt
(self, line, dataset=None)
VLMEvalKit/vlmeval/vlm/mmalaya.py:262
↓ 1 callersMethodbuild_multi_choice_prompt
(self, line, dataset=None)
VLMEvalKit/vlmeval/vlm/internvl_chat.py:187
↓ 1 callersMethodbuild_multi_choice_prompt
(self, line, dataset=None)
VLMEvalKit/vlmeval/vlm/parrot.py:93
↓ 1 callersMethodbuild_multi_choice_prompt
(self, line, dataset=None)
VLMEvalKit/vlmeval/vlm/ovis.py:78
↓ 1 callersMethodbuild_multi_choice_prompt
(self, line, dataset=None)
VLMEvalKit/vlmeval/vlm/vispeak/vispeak_qwen2.py:94
↓ 1 callersMethodbuild_multi_choice_prompt
(self, line, dataset=None)
VLMEvalKit/vlmeval/api/sensechat_vision.py:86
↓ 1 callersFunctionbuild_option_str
(option_dict)
VLMEvalKit/vlmeval/smp/vlm.py:116
↓ 1 callersFunctionbuild_prompt
(question, options, prediction)
VLMEvalKit/vlmeval/dataset/utils/multiple_choice.py:154
↓ 1 callersFunctionbuild_prompt_blink
(question, options, prediction)
VLMEvalKit/vlmeval/dataset/utils/multiple_choice.py:174
↓ 1 callersFunctionbuild_prompt_cn
(question, options, prediction)
VLMEvalKit/vlmeval/dataset/utils/multiple_choice.py:208
↓ 1 callersMethodbuild_prompt_mathvista
(self, message)
VLMEvalKit/vlmeval/vlm/idefics.py:203
↓ 1 callersMethodbuild_prompt_mmbench
(self, message)
VLMEvalKit/vlmeval/vlm/idefics.py:146
↓ 1 callersMethodbuild_prompt_mmmu
(self, message)
VLMEvalKit/vlmeval/vlm/idefics.py:173
↓ 1 callersMethodbuild_prompt_mt
(self, message)
VLMEvalKit/vlmeval/vlm/idefics.py:129
↓ 1 callersMethodbuild_prompt_nopack
(self, line, num_frames, video_llm)
VLMEvalKit/vlmeval/dataset/mmbench_video.py:113
↓ 1 callersMethodbuild_prompt_pack
(self, line, num_frames)
VLMEvalKit/vlmeval/dataset/mmbench_video.py:91
↓ 1 callersMethodbuild_prompt_puremcq
(self, message)
VLMEvalKit/vlmeval/vlm/idefics.py:109
↓ 1 callersFunctionbuild_transform
(input_size)
VLMEvalKit/vlmeval/vlm/internvl_chat.py:22
↓ 1 callersMethodbuilt_yorn_prompt
(self, line, dataset=None)
VLMEvalKit/vlmeval/vlm/parrot.py:82
↓ 1 callersMethodbuilt_yorn_prompt
(self, line, dataset=None)
VLMEvalKit/vlmeval/vlm/ovis.py:70
↓ 1 callersMethodcalculat_metric
(self, ans)
VLMEvalKit/vlmeval/dataset/image_mt.py:61
↓ 1 callersMethodcalculate_score_forward
(self, results)
OVO-Bench/utils/OVOBenchScore.py:30
↓ 1 callersMethodcall_for_batch
( self, output_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs )
vispeak/util/mm_utils.py:143
↓ 1 callersFunctioncan_infer_option
(answer, choices)
VLMEvalKit/vlmeval/utils/matching_util.py:7
↓ 1 callersFunctioncan_infer_text
(answer, choices)
VLMEvalKit/vlmeval/utils/matching_util.py:51
↓ 1 callersFunctionchange_file
(file_path, mm_vision_tower)
VLMEvalKit/vlmeval/vlm/video_llm/llama_vid.py:23
↓ 1 callersMethodchat_inner
(self, message, dataset=None)
VLMEvalKit/vlmeval/vlm/idefics.py:235
↓ 1 callersMethodchat_inner
(self, inputs, **kwargs)
VLMEvalKit/vlmeval/api/base.py:141
↓ 1 callersMethodchat_inner_v2
(self, message, dataset=None)
VLMEvalKit/vlmeval/vlm/internvl_chat.py:401
↓ 1 callersFunctionchat_mt
(model, messages, dataset_name)
VLMEvalKit/vlmeval/inference_mt.py:20
↓ 1 callersFunctioncheck_denotation
Return True if the predicted denotation is correct. Args: target_values (list[Value]) predicted_values (list[Value]) Returns:
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:456
↓ 1 callersMethodcheck_install
(self)
VLMEvalKit/vlmeval/vlm/deepseek_vl.py:13
↓ 1 callersFunctioncollect_error_files
(log_file_path)
data_tools/mmco_collect.py:3
↓ 1 callersFunctioncompleted
(m, d, suf)
VLMEvalKit/vlmeval/tools.py:101
↓ 1 callersMethodcompute_scores
(self)
VLMEvalKit/vlmeval/dataset/image_caption.py:20
↓ 1 callersFunctioncompute_value
Compute the value. When current unit is larger than previous unit, current unit * all previous units will be used as all previous uni
audio_eval/cn_tn.py:624
↓ 1 callersFunctioncompute_wer
(refs, hyps, language)
audio_eval/eval_asr.py:168
↓ 1 callersFunctionconcat_item
(items)
data_tools/concat_data_patch_qwen.py:66
↓ 1 callersFunctioncorrect_symbols
一百八 to 一百八十 一亿一千三百万 to 一亿 一千万 三百万
audio_eval/cn_tn.py:590
↓ 1 callersFunctioncount
(args)
StreamingBench/src/data/count.py:6
↓ 1 callersMethoddate2chntext
(self)
audio_eval/cn_tn.py:872
↓ 1 callersFunctiondefault_rating
(data_file)
VLMEvalKit/vlmeval/dataset/utils/yorn.py:144
↓ 1 callersFunctiondetermine_dataset
(eval_file)
VLMEvalKit/scripts/mmb_eval_gradio.py:45
↓ 1 callersFunctiondisable_torch_init
Disable the redundant torch default initialization to accelerate model creation.
vispeak/util/utils.py:14
↓ 1 callersFunctiondisable_torch_init
Disable the redundant torch default initialization to accelerate model creation.
VLMEvalKit/vlmeval/vlm/yi_vl.py:43
↓ 1 callersFunctiondo_setup
()
VLMEvalKit/setup.py:87
↓ 1 callersMethoddump_image
(self, line)
VLMEvalKit/vlmeval/dataset/image_base.py:98
↓ 1 callersMethoddump_image
Dump the image(s) of the input line to the corresponding dataset folder. Args: line (line of pd.DataFrame): The raw input line.
VLMEvalKit/vlmeval/api/sensechat_vision.py:31
↓ 1 callersFunctiondynamic_preprocess
( image, min_num=2, max_num=12, image_size=448, use_thumbnail=False, img_mean=0 )
data_tools/statistics_token_num_frameCat.py:47
↓ 1 callersFunctiondynamic_preprocess
(image, min_num=1, max_num=12, image_size=448, use_thumbnail=True)
data_tools/concat_data_patch_qwen.py:32
↓ 1 callersFunctiondynamic_preprocess
(image, min_num=1, max_num=12, image_size=448, use_thumbnail=True)
data_tools/statistics_token_num_patch.py:40
↓ 1 callersFunctiondynamic_preprocess
(image, min_num=1, max_num=12, image_size=448, use_thumbnail=True)
data_tools/statistics_token_num_patch_video.py:50
↓ 1 callersFunctiondynamic_preprocess
( image, min_num=1, max_num=6, image_size=448, use_thumbnail=False )
VLMEvalKit/vlmeval/vlm/mmalaya.py:101
↓ 1 callersFunctiondynamic_preprocess
(image, min_num=1, max_num=6, image_size=448, use_thumbnail=False)
VLMEvalKit/vlmeval/vlm/internvl_chat.py:49
↓ 1 callersMethodembed_gst
(self, x)
vispeak/model/vita_tts/decoder/ticodec/models.py:703
↓ 1 callersMethodencode_jwt_token
(self, ak, sk)
VLMEvalKit/vlmeval/api/sensechat_vision.py:71
↓ 1 callersMethodeval
Evaluate the model on the given data and update the data with the model responses. data: data input model: model to evaluate
StreamingBench/src/benchmark/Benchmark.py:9
↓ 1 callersMethodeval
(self, data, model, output_path)
StreamingBench/src/benchmark/StreamingBenchOmni.py:28
↓ 1 callersFunctioneval_score
(gt, pred, answer_type)
VLMEvalKit/vlmeval/dataset/mmlongbench.py:296
↓ 1 callersFunctionevaluate_fintabnet
(data, score_keys)
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:129
↓ 1 callersFunctionevaluate_tabfact
(data, score_keys)
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:56
↓ 1 callersFunctionevaluate_wtq
(data, score_keys)
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:94
↓ 1 callersMethodexpand2square
(self, pil_img, background_color)
vispeak/model/language_model/vispeak_qwen2.py:671
↓ 1 callersFunctionexpand_question_into_multimodal
( question_text, image_token_len, im_st_token, im_ed_token, im_patch_token )
VLMEvalKit/vlmeval/vlm/omnilmm.py:55
↓ 1 callersFunctionextract_json_objects
(text, decoder=JSONDecoder())
VLMEvalKit/vlmeval/smp/misc.py:206
↓ 1 callersFunctionextract_segments
(audio_file, sample_points, audio_segments_path, num_audio_seg)
VLMEvalKit/vlmeval/dataset/videomme.py:36
↓ 1 callersFunctionextract_segments
(audio_file, sample_points, audio_segments_path)
VLMEvalKit/vlmeval/dataset/mvbench.py:32
← previousnext →301–400 of 1,447, ranked by callers