MCPcopy Create free account

hub / github.com/OpenBMB/MiniCPM-V / functions

Functions1,137 in github.com/OpenBMB/MiniCPM-V

⨍ Functions 1,137◇ Types & classes 141↳ Endpoints 6
↓ 196 callersFunctionload
(f, fmt=None)
eval_mm/vlmevalkit/vlmeval/smp/file.py:162
↓ 120 callersFunctiondump
(data, f, **kwargs)
eval_mm/vlmevalkit/vlmeval/smp/file.py:136
↓ 50 callersFunctionlistinstr
(lst, s)
eval_mm/vlmevalkit/vlmeval/smp/misc.py:118
↓ 39 callersFunctionbuild_judge
(**kwargs)
eval_mm/vlmevalkit/vlmeval/dataset/utils/judge_util.py:7
↓ 34 callersFunctionmd5
(s)
eval_mm/vlmevalkit/vlmeval/smp/file.py:278
↓ 30 callersFunctiontrack_progress_rich
( func: Callable, tasks: Iterable = tuple(), nproc: int = 1, save=None,
eval_mm/vlmevalkit/vlmeval/utils/mp_util.py:14
↓ 28 callersMethodgenerate
(self, message, dataset=None)
eval_mm/vlmevalkit/vlmeval/api/gpt.py:266
↓ 24 callersFunctionDATASET_TYPE
(dataset, *, default: str = 'MCQ')
eval_mm/vlmevalkit/vlmeval/dataset/__init__.py:163
↓ 24 callersFunctionLMUDataRoot
()
eval_mm/vlmevalkit/vlmeval/smp/file.py:68
↓ 24 callersMethodworking
If the API model is working, return True, else return False. Returns: bool: If the API model is working, return True, else return
eval_mm/vlmevalkit/vlmeval/api/base.py:59
↓ 22 callersFunctiontoliststr
(s)
eval_mm/vlmevalkit/vlmeval/smp/misc.py:243
↓ 20 callersMethodcopy
(self)
omnilmm/conversation.py:142
↓ 20 callersFunctionmodelscope_flag_set
()
eval_mm/vlmevalkit/vlmeval/smp/misc.py:28
↓ 18 callersMethodwrite
(self, buf)
omnilmm/utils.py:74
↓ 17 callersFunctiondecode_base64_to_image_file
(base64_string, image_path, target_size=-1)
eval_mm/vlmevalkit/vlmeval/smp/vlm.py:111
↓ 17 callersFunctionget_logger
(name, log_file=None, log_level=logging.INFO, file_mode='w')
eval_mm/vlmevalkit/vlmeval/smp/log.py:9
↓ 17 callersFunctionread_ok
(img_path)
eval_mm/vlmevalkit/vlmeval/smp/vlm.py:128
↓ 16 callersFunctionmilliseconds_to_seconds
(milliseconds)
eval_mm/vlmevalkit/vlmeval/dataset/utils/cgbench.py:282
↓ 15 callersMethoddecode
(self, image, input_ids)
chat.py:95
↓ 15 callersFunctionget_cache_path
(repo_id, branch='main', repo_type='datasets')
eval_mm/vlmevalkit/vlmeval/smp/misc.py:80
↓ 14 callersMethodframe_paths
(self, video)
eval_mm/vlmevalkit/vlmeval/dataset/video_base.py:57
↓ 13 callersMethodframe_paths_fps
(self, video, num_frames)
eval_mm/vlmevalkit/vlmeval/dataset/video_base.py:62
↓ 13 callersFunctiongpt_key_set
()
eval_mm/vlmevalkit/vlmeval/smp/vlm.py:139
↓ 12 callersMethodchat
(self, input)
chat.py:145
↓ 11 callersFunctionget_dimension_rating
(data_path)
eval_mm/vlmevalkit/vlmeval/dataset/utils/mlvu.py:181
↓ 11 callersFunctionget_rank_and_world_size
()
eval_mm/vlmevalkit/vlmeval/smp/misc.py:110
↓ 10 callersFunctionLOCALIZE
(fname, new_fname=None)
eval_mm/vlmevalkit/vlmeval/tools.py:254
↓ 10 callersMethodbuild_prompt
Build custom prompts for a specific dataset. Called only if `use_custom_prompt` returns True. Args: line (line of pd.DataFrame):
eval_mm/vlmevalkit/vlmeval/vlm/base.py:27
↓ 9 callersMethodclose
()
web_demos/minicpm-o_2.6/web_server/src/utils/websocket.js:70
↓ 9 callersFunctionsample_frames_clue_average
(clues_time_intervals, frame_num, fps)
eval_mm/vlmevalkit/vlmeval/dataset/utils/cgbench.py:286
↓ 8 callersMethodcheck_content
Check the content type of the input. Four types are allowed: str, dict, liststr, listdict. Args: msgs: Raw input messages.
eval_mm/vlmevalkit/vlmeval/api/base.py:83
↓ 8 callersFunctioncreate_component
(params, comp='Slider')
web_demos/web_demo_2.5.py:110
↓ 8 callersFunctioncreate_component
(params, comp='Slider')
web_demos/web_demo.py:117
↓ 8 callersFunctiond2df
(D)
eval_mm/vlmevalkit/vlmeval/smp/misc.py:125
↓ 8 callersMethoddump_image
(self, origin_line)
eval_mm/vlmevalkit/vlmeval/dataset/dude.py:88
↓ 8 callersFunctionencode_image_to_base64
(img, target_size=-1, fmt='JPEG')
eval_mm/vlmevalkit/vlmeval/smp/vlm.py:82
↓ 8 callersFunctionfile_size
(f, unit='GB')
eval_mm/vlmevalkit/vlmeval/smp/file.py:330
↓ 8 callersFunctionmake_text
(text)
web_demos/web_demo_2.6.py:218
↓ 8 callersFunctionmake_text
(text)
web_demos/minicpm-o_2.6/chatbot_web_demo_o2.6.py:213
↓ 7 callersFunctioncan_infer
(answer, choices)
eval_mm/vlmevalkit/vlmeval/utils/matching_util.py:66
↓ 7 callersMethodchat
The main function for multi-turn chatting. Will call `chat_inner` with the preprocessed input messages.
eval_mm/vlmevalkit/vlmeval/api/base.py:155
↓ 7 callersMethodcheck_content
Check the content type of the input. Four types are allowed: str, dict, liststr, listdict.
eval_mm/vlmevalkit/vlmeval/vlm/base.py:49
↓ 7 callersFunctiondownload_file
(url, filename=None)
eval_mm/vlmevalkit/vlmeval/smp/file.py:194
↓ 7 callersFunctionmerge_intervals
Merge overlapping intervals in a list. Assumes each interval is a list [start, end].
eval_mm/vlmevalkit/vlmeval/dataset/utils/cgbench.py:304
↓ 6 callersFunctionextract_answer_from_item
(model, item, dataset_name=None)
eval_mm/vlmevalkit/vlmeval/dataset/utils/multiple_choice.py:262
↓ 6 callersFunctionget_clean_string
(s)
eval_mm/vlmevalkit/vlmeval/dataset/mmlongbench.py:142
↓ 6 callersMethodget_subtitles
(self, subtitle_path, frame_indices=None, fps=None, sub_time=False)
eval_mm/vlmevalkit/vlmeval/dataset/cgbench.py:103
↓ 6 callersMethodget_subtitles
(self, subtitle_path, frame_indices=None, fps=None, sub_time=False)
eval_mm/vlmevalkit/vlmeval/dataset/cgbench.py:978
↓ 6 callersFunctionget_timestampes
(frame_indices, fps)
eval_mm/vlmevalkit/vlmeval/dataset/utils/cgbench.py:426
↓ 6 callersFunctionistype
(s, type)
eval_mm/vlmevalkit/vlmeval/smp/misc.py:66
↓ 6 callersFunctionremap
(data_in, tup, off)
eval_mm/vlmevalkit/vlmeval/tools.py:178
↓ 6 callersFunctionunzip_hf_zip
(pth)
eval_mm/vlmevalkit/vlmeval/dataset/utils/cgbench.py:585
↓ 5 callersFunctionbuild_dataset
(dataset_name, **kwargs)
eval_mm/vlmevalkit/vlmeval/dataset/__init__.py:204
↓ 5 callersMethodchat
The main function for multi-turn chatting. Will call `chat_inner` with the preprocessed input messages.
eval_mm/vlmevalkit/vlmeval/vlm/base.py:117
↓ 5 callersMethodclear
(self)
web_demos/minicpm-o_2.6/model_server.py:290
↓ 5 callersMethodemit
(event, ...args)
web_demos/minicpm-o_2.6/web_server/src/utils/websocket.js:64
↓ 5 callersFunctionextract_answer
Extracts the answer from the output string based on the task type. Parameters: output_string (str): The output string. task_type (st
eval_mm/vlmevalkit/vlmeval/dataset/utils/naturalbench.py:4
↓ 5 callersFunctionextract_characters_regex
(s)
eval_mm/vlmevalkit/vlmeval/dataset/utils/videomme.py:128
↓ 5 callersFunctionhit_calculate
(result, dataset_name, anls_threshold=0.5)
eval_mm/vlmevalkit/vlmeval/dataset/utils/vqa_eval.py:160
↓ 5 callersFunctionmcq_vanilla_eval
(model, data, meta, nproc, result_file, dataset_name=None)
eval_mm/vlmevalkit/vlmeval/dataset/utils/multiple_choice.py:364
↓ 5 callersFunctionnormalize_dict
Sort by value, while iterate over element if data is list
eval_mm/vlmevalkit/vlmeval/dataset/utils/ccocr_evaluator/kie_evaluator.py:92
↓ 5 callersMethodprocessDigitArticle
(self, inText)
eval_mm/vlmevalkit/vlmeval/dataset/utils/mmniah.py:231
↓ 5 callersMethodprocessPunctuation
(self, inText)
eval_mm/vlmevalkit/vlmeval/dataset/utils/mmniah.py:219
↓ 5 callersMethodrename
Compares attributes of trees
eval_mm/vlmevalkit/vlmeval/dataset/utils/ccocr_evaluator/doc_parsing_evaluator.py:59
↓ 4 callersFunctionanls_compute
(groundtruth, prediction, threshold=0.5)
eval_mm/vlmevalkit/vlmeval/dataset/mmlongbench.py:102
↓ 4 callersMethodbuild_prompt
(self, line)
eval_mm/vlmevalkit/vlmeval/dataset/image_vqa.py:1063
↓ 4 callersFunctioncalculate_acc_at_iou
(scores)
eval_mm/vlmevalkit/vlmeval/dataset/utils/cgbench.py:218
↓ 4 callersFunctioncalculate_crr
(scores)
eval_mm/vlmevalkit/vlmeval/dataset/utils/cgbench.py:177
↓ 4 callersFunctioncalculate_rec_at_iou
(scores)
eval_mm/vlmevalkit/vlmeval/dataset/utils/cgbench.py:255
↓ 4 callersMethoddump_image
(self, line, dataset)
eval_mm/vlmevalkit/vlmeval/vlm/base.py:42
↓ 4 callersFunctionencode_image
(image)
web_demos/web_demo_2.6.py:153
↓ 4 callersFunctionencode_image
(image)
web_demos/minicpm-o_2.6/chatbot_web_demo_o2.6.py:148
↓ 4 callersFunctionenhance_level_to_args
(MAX_LEVEL)
omnilmm/model/utils.py:290
↓ 4 callersFunctionensure_divide
(length, patch_size)
finetune/dataset.py:497
↓ 4 callersFunctionfind_word_position
(string, word)
eval_mm/vlmevalkit/vlmeval/dataset/utils/naturalbench.py:20
↓ 4 callersMethodgenerate_end
(self)
web_demos/minicpm-o_2.6/model_server.py:482
↓ 4 callersMethodjudge
(self, expression1, expression2, precision=1e-8)
eval_mm/vlmevalkit/vlmeval/dataset/utils/olympiadbench.py:139
↓ 4 callersFunctionload_env
()
eval_mm/vlmevalkit/vlmeval/smp/misc.py:197
↓ 4 callersFunctionnormalize
(x)
eval_mm/vlmevalkit/vlmeval/dataset/utils/tablevqabench.py:209
↓ 4 callersFunctionnormalize_values_of_nested_dict
eval_mm/vlmevalkit/vlmeval/dataset/utils/ccocr_evaluator/kie_evaluator.py:275
↓ 4 callersMethodparse
Try to parse into a date. Return: tuple (year, month, date) if successful; otherwise None.
eval_mm/vlmevalkit/vlmeval/dataset/utils/tablevqabench.py:385
↓ 4 callersFunctionparse_file
(s)
eval_mm/vlmevalkit/vlmeval/smp/file.py:297
↓ 4 callersFunctionprocess_answer
(answer)
eval_mm/vlmevalkit/vlmeval/dataset/utils/vqa_eval.py:239
↓ 4 callersFunctionrank0_print
(*args)
finetune/finetune.py:73
↓ 4 callersMethodread_parquet
(pth)
eval_mm/vlmevalkit/vlmeval/dataset/tempcompass.py:96
↓ 4 callersMethodsave_video_frames
(self, video, uid, clue_intervals=None, num_frames=8, fps=-1)
eval_mm/vlmevalkit/vlmeval/dataset/cgbench.py:349
↓ 4 callersMethodsave_video_frames
(self, video, uid, clue_intervals=None, num_frames=8, fps=-1)
eval_mm/vlmevalkit/vlmeval/dataset/cgbench.py:1229
↓ 4 callersMethodsupported_datasets
(cls)
eval_mm/vlmevalkit/vlmeval/dataset/__init__.py:102
↓ 4 callersMethodsympy_sub_pi
(self, expression_sympy)
eval_mm/vlmevalkit/vlmeval/dataset/mmmath.py:147
↓ 4 callersFunctiontrim_and_pad
(seq, batch_first, padding_value)
finetune/dataset.py:89
↓ 4 callersMethodupdate_last_request_time
(self)
web_demos/minicpm-o_2.6/model_server.py:136
↓ 4 callersMethoduse_custom_prompt
Whether to use custom prompt for the given dataset. Args: dataset (str): The name of the dataset. Returns: b
eval_mm/vlmevalkit/vlmeval/vlm/base.py:14
↓ 4 callersFunctionwriteString
(view, offset, string)
web_demos/minicpm-o_2.6/web_server/src/views/home/components/merge.js:37
↓ 4 callersFunctionwriteString
(view, offset, string)
web_demos/minicpm-o_2.6/web_server/src/hooks/useVoice.js:1
↓ 3 callersFunctionMMLongBench_auxeval
(model, line)
eval_mm/vlmevalkit/vlmeval/dataset/mmlongbench.py:342
↓ 3 callersMethod__init__
( self, dataset="CG-Bench_OpenEnded", use_subtitle=False, use_subtitle_time=Fa
eval_mm/vlmevalkit/vlmeval/dataset/cgbench.py:1378
↓ 3 callersMethod__init__
(self, dataset='TempCompass', nframe=0, fps=-1)
eval_mm/vlmevalkit/vlmeval/dataset/tempcompass.py:19
↓ 3 callersFunctionacc
(key)
eval_mm/vlmevalkit/vlmeval/dataset/utils/yorn.py:29
↓ 3 callersFunctionbuild_transform
(is_train, randaug=True, input_size=224, interpolation='bicubic', std_mode='IMAGENET_INCEPTION')
omnilmm/model/utils.py:421
↓ 3 callersFunctioncalc_aAcc
(data)
eval_mm/vlmevalkit/vlmeval/dataset/utils/yorn.py:108
next →1–100 of 1,137, ranked by callers