MCPcopy Create free account

hub / github.com/FeiElysia/Tempo / functions

Functions7,449 in github.com/FeiElysia/Tempo

⨍ Functions 7,449◇ Types & classes 488↳ Endpoints 41
↓ 8 callersFunctiontextcaps_aggregation_result
(results, metric, args=None)
lmms_eval/tasks/textcaps/utils.py:39
↓ 8 callersFunctionvatex_aggregation_result
(results, metric, args=None)
lmms_eval/tasks/vatex/utils.py:120
↓ 8 callersFunctionyoucook2_aggregate_results
(results, metric, **kwargs)
lmms_eval/tasks/youcook2/utils.py:61
↓ 7 callersFunction_aggregate_by_category
(results, category)
lmms_eval/tasks/perceptioncomp/utils.py:259
↓ 7 callersFunction_aggregate_by_question_type
(results, question_type)
lmms_eval/tasks/video_holmes/utils.py:243
↓ 7 callersMethod_write_watchdog_heartbeat
(self, phase: str, batch_idx: int, batch_requests=None)
lmms_eval/models/simple/vllm.py:305
↓ 7 callersFunctioncal_per_metrics
(pred, gt)
lmms_eval/tasks/ocrbench_v2/page_ocr_metric.py:14
↓ 7 callersFunctionfmt_se
(se_val)
lmms_eval/utils.py:578
↓ 7 callersMethodget_vision_tower_aux_list
(self)
tempo/tempo_arch.py:52
↓ 7 callersFunctionis_budget_exceeded
Return whether the configured token budget has been exceeded. Reading a ``bool`` is atomic in CPython, so no lock is needed. The worst-case
lmms_eval/models/model_utils/usage_metrics.py:130
↓ 7 callersFunctionnum2chn
(number_string, numbering_type=NUMBERING_TYPES[1], big=False, traditional=False, alt_zero=False, alt_one=False
lmms_eval/tasks/librispeech/cn_tn.py:645
↓ 7 callersMethodprocess_images
(self, images, image_processor, model_cfg)
lmms_eval/models/simple/auroracap.py:216
↓ 7 callersFunctionrefcoco_bbox_rec_aggregation_result
Aggregate the results of the RefCOCO evaluation task using the specified metric. Args: - results (list of dict): List of result dictiona
lmms_eval/tasks/refcoco+/utils_rec.py:163
↓ 7 callersFunctionrefcoco_bbox_rec_aggregation_result
Aggregate the results of the RefCOCO evaluation task using the specified metric. Args: - results (list of dict): List of result dictiona
lmms_eval/tasks/refcoco/utils_rec.py:163
↓ 7 callersFunctionrefcoco_bbox_rec_aggregation_result
Aggregate the results of the RefCOCO evaluation task using the specified metric. Args: - results (list of dict): List of result dictiona
lmms_eval/tasks/refcocog/utils_rec.py:163
↓ 7 callersFunctionscreenspot_rec_aggregation_result
Aggregate the results of the screenspot evaluation task using the specified metric. Args: - results (list of dict): List of result dicti
lmms_eval/tasks/screenspot/utils_rec.py:126
↓ 7 callersFunctionvalidate_point_inside_bounds
(x, y, imWidth, imHeight)
lmms_eval/tasks/ocrbench_v2/spotting_eval/rrc_evaluation_funcs_1_1.py:303
↓ 6 callersFunction_aggregate_all_category
(results, categories)
lmms_eval/tasks/salbench/utils.py:132
↓ 6 callersFunction_aggregate_by_category
(results, category: str)
lmms_eval/tasks/structeditbench/utils.py:454
↓ 6 callersFunction_aggregate_category_acc
(results, target_category: str)
lmms_eval/tasks/sitebench/utils.py:297
↓ 6 callersFunction_aggregate_category_caa
(results, target_category: str)
lmms_eval/tasks/sitebench/utils.py:307
↓ 6 callersFunction_clean_answer_text
(answer: str)
lmms_eval/tasks/mathcanvas/utils.py:75
↓ 6 callersFunction_clean_string
(value: Any)
lmms_eval/tasks/mmlongbench_doc/utils.py:38
↓ 6 callersFunction_compute_all_subscores
Compute all sub-scores at once. Returns dict with keys: overall, relevance, logic, level_1, level_2, level_3.
lmms_eval/tasks/videomme_v2/utils.py:262
↓ 6 callersMethod_create_numeric_node
(self, value)
lmms_eval/models/model_utils/thyme/sandbox.py:218
↓ 6 callersMethod_get_numeric_value
(self, node_value)
lmms_eval/models/model_utils/thyme/sandbox.py:211
↓ 6 callersFunction_normalize_response
(text: str)
lmms_eval/tasks/safety_redteam/utils.py:84
↓ 6 callersFunction_normalize_whitespace
(text: str)
lmms_eval/tasks/motionbench/utils.py:25
↓ 6 callersFunction_parse_json_list
(raw: str)
lmms_eval/tasks/uni_mmmu/utils.py:93
↓ 6 callersFunctioncalculate_ins_level_acc
Calculate the instruction level accuracy for given Subject results https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445782686b4c35
lmms_eval/tasks/jmmmu_pro/utils.py:346
↓ 6 callersMethodclose
(self)
lmms_eval/caching/response_cache.py:852
↓ 6 callersFunctionconvert_markdown_table_to_html
Converts a markdown table to the corresponding html string for TEDS computation.
lmms_eval/tasks/ocrbench_v2/TEDS_metric.py:176
↓ 6 callersMethoddoc_to_text
(self, doc)
lmms_eval/api/task.py:415
↓ 6 callersFunctionencode_image_to_data_url
( image: ImageInput, *, image_format: str = "PNG", mime_type: Optional[str] = None, conver
lmms_eval/models/model_utils/media_encoder.py:142
↓ 6 callersMethodeval_result
(self, results, eval_method)
lmms_eval/tasks/mmbench/mmbench_evals.py:252
↓ 6 callersFunctionexpand2square
(pil_img, background_color)
tempo/mm_datautils.py:192
↓ 6 callersMethodget_chat_response
(self, prompt, temperature=0, max_tokens=256, n=1, patience=10000000, sleep_time=0)
lmms_eval/tasks/mmrefine/mmrefine_evals.py:48
↓ 6 callersFunctionget_wups
calculate the wups score :param pred: :param truth: :return:
lmms_eval/tasks/nextqa/utils.py:232
↓ 6 callersFunctionhash_string
(string: str)
lmms_eval/utils.py:57
↓ 6 callersFunctionis_video_file
(file_path: str)
lmms_eval/models/simple/cambrians.py:36
↓ 6 callersFunctionlevenshtein_distance
(s1, s2)
lmms_eval/tasks/ocrbench_v2/vqa_metric.py:5
↓ 6 callersMethodlist_all_tasks
(self, list_groups=True, list_tags=True, list_subtasks=True)
lmms_eval/tasks/__init__.py:97
↓ 6 callersFunctionlistinstr
(lst, s)
lmms_eval/models/simple/xcomposer2_4KHD.py:273
↓ 6 callersFunctionmake_table
Generate table of results. Automatically hides columns that are all N/A (e.g., stability metrics when repeats=1, or baseline comparison when
lmms_eval/utils.py:540
↓ 6 callersFunctionnormalize_facing
Normalize facing field to standard direction. Args: facing: The facing value to normalize Returns: Normalized facing directi
lmms_eval/tasks/spatialtreebench/metrics/mindcube_cogmap/src/evaluation/cogmap/graph_operations.py:128
↓ 6 callersFunctionparse_score
(review)
lmms_eval/tasks/videochatgpt/utils.py:424
↓ 6 callersMethodtest_docs
:return: Iterable[obj] A iterable of any object, that doc_to_text can handle
lmms_eval/api/task.py:365
↓ 6 callersMethodtokenizer
(self)
lmms_eval/models/simple/ola.py:219
↓ 6 callersMethodvalidation_docs
:return: Iterable[obj] A iterable of any object, that doc_to_text can handle
lmms_eval/api/task.py:358
↓ 6 callersFunctionwrap_html_table
The TEDS computation from PubTabNet code requires that the input html table should have <html>, <body>, and <table> tags. Add them if they ar
lmms_eval/tasks/ocrbench_v2/TEDS_metric.py:498
↓ 5 callersFunction_append_cache_entry
(cache, key_states, value_states, modality, length, surprise_score)
lmms_eval/models/simple/cambrians_vsr.py:72
↓ 5 callersFunction_extract_first_number
(value: Any)
lmms_eval/tasks/mmlongbench_doc/utils.py:86
↓ 5 callersFunction_flatten
(text: object)
lmms_eval/cli/power_utils.py:16
↓ 5 callersMethod_generate_editing
Image editing mode: Generate edited images
lmms_eval/models/simple/qwen_image_edit.py:830
↓ 5 callersMethod_generate_understanding
Image understanding mode: VQA using Qwen2.5-VL
lmms_eval/models/simple/qwen_image_edit.py:751
↓ 5 callersMethod_name_is_registered
(self, name)
lmms_eval/tasks/__init__.py:162
↓ 5 callersFunction_parse_json_like
(candidate)
lmms_eval/tasks/tau2_bench/utils.py:32
↓ 5 callersMethod_request
(self, method: str, endpoint: str, **kwargs)
lmms_eval/entrypoints/client.py:345
↓ 5 callersFunction_viewspatial_aggregate_by_type
Aggregate accuracy for a specific question type.
lmms_eval/tasks/viewspatial/utils.py:88
↓ 5 callersMethodapply
Defines the operation to perform on a list of the `inst.resps` properties of `Instance` objects. Should return the list of (filtered)
lmms_eval/api/filter.py:23
↓ 5 callersMethodcardinal2chntext
(self)
lmms_eval/tasks/librispeech/cn_tn.py:746
↓ 5 callersFunctioncompute_accuracy
Compute the accuracy of two bounding boxes based on a specified threshold. Parameters: - box1 (list of float): Bounding box [x_min, y_mi
lmms_eval/tasks/refcoco+/utils_rec.py:128
↓ 5 callersFunctioncompute_accuracy
Compute the accuracy of two bounding boxes based on a specified threshold. Parameters: - box1 (list of float): Bounding box [x_min, y_mi
lmms_eval/tasks/refcoco/utils_rec.py:128
↓ 5 callersFunctioncompute_accuracy
Compute the accuracy of two bounding boxes based on a specified threshold. Parameters: - box1 (list of float): Bounding box [x_min, y_mi
lmms_eval/tasks/screenspot/utils_rec.py:91
↓ 5 callersFunctioncompute_accuracy
Compute the accuracy of two bounding boxes based on a specified threshold. Parameters: - box1 (list of float): Bounding box [x_min, y_mi
lmms_eval/tasks/refcocog/utils_rec.py:128
↓ 5 callersFunctionconvert_str_to_dict
Parses the 'predict' string and returns a dictionary. Missing or unparseable content is handled gracefully. Parameters: - predict_st
lmms_eval/tasks/ocrbench_v2/TEDS_metric.py:211
↓ 5 callersMethoddevice
(self)
lmms_eval/models/simple/ola.py:252
↓ 5 callersMethoddownload
Downloads and returns the task dataset. Override this method to download the dataset from a custom API. :param data_dir: str
lmms_eval/api/task.py:279
↓ 5 callersFunctiondownsample_audio
(audio_array: np.ndarray, original_sr: int, target_sr: int)
lmms_eval/models/model_utils/audio_processing.py:7
↓ 5 callersMethodevaluate_async
Asynchronously evaluate the given request and return a response Args: request: JudgeRequest containing the evaluation co
lmms_eval/llm_judge/base.py:112
↓ 5 callersFunctionextract_json_from_text
Extract JSON cognitive map from text response. Returns the JSON object if found, otherwise None. Args: text: Text containing a JSON o
lmms_eval/tasks/spatialtreebench/metrics/mindcube_cogmap/src/evaluation/core/extractors.py:95
↓ 5 callersMethodflatten
Flatten a nested list.
lmms_eval/models/chat/internvl_hf.py:199
↓ 5 callersMethodflatten
(self, input)
lmms_eval/models/chat/huggingface.py:178
↓ 5 callersFunctionget_column_value
(doc, candidates)
lmms_eval/tasks/voicebench/utils.py:20
↓ 5 callersFunctionget_eval_generic
(question, answer, pred, task, max_tokens: int, retries: int = 5)
lmms_eval/tasks/videochatgpt/utils.py:214
↓ 5 callersFunctionload_defualt_config
()
lmms_eval/tasks/plm_videobench/eval_utils.py:293
↓ 5 callersMethodnormalize_dict
Sort by value, while iterate over element if data is list
lmms_eval/tasks/synthdog/donut_evaluator.py:87
↓ 5 callersFunctionparse_mmmu_multi_choice_response
(response, all_choices, index2ans)
lmms_eval/tasks/_task_utils/mmmu_mcq_utils.py:17
↓ 5 callersFunctionpreprocess
(text)
lmms_eval/tasks/gpqa/cot_zeroshot/utils.py:7
↓ 5 callersFunctionpreprocess
(text)
lmms_eval/tasks/gpqa/n_shot/utils.py:7
↓ 5 callersFunctionpreprocess
(text)
lmms_eval/tasks/gpqa/zeroshot/utils.py:7
↓ 5 callersFunctionpreprocess
(text)
lmms_eval/tasks/gpqa/generative/utils.py:7
↓ 5 callersFunctionpreprocess
(text)
lmms_eval/tasks/gpqa/cot_n_shot/utils.py:7
↓ 5 callersFunctionpreprocess
(text)
lmms_eval/tasks/gpqa/reasoning/utils.py:20
↓ 5 callersMethodsample
Draw the first `n` samples in order from the specified split. Used for tasks with "canonical" ordered fewshot examples, such as MMLU
lmms_eval/api/samplers.py:59
↓ 5 callersFunctionsimple_parse_args_string
Parses something like args1=val1,arg2=val2 Into a dictionary Handles JSON values with nested commas, e.g., arg='{"key1":val1,"key
lmms_eval/utils.py:206
↓ 5 callersFunctionstr_to_bboxes
(bbox_list)
lmms_eval/tasks/megabench/metrics/scoring/common/conversions.py:96
↓ 5 callersMethodword_tokenize
(self, word)
lmms_eval/tasks/_task_utils/vqa_eval_metric.py:178
↓ 4 callersFunction_aggregate
(results: List[Dict[str, Any]], target_type: Optional[str] = None)
lmms_eval/tasks/osworld_g/utils.py:149
↓ 4 callersFunction_aggregate_formula_edit
Weighted average of formula edit distances across pages.
lmms_eval/tasks/omnidocbench/utils.py:736
↓ 4 callersFunction_aggregate_metric
(results, metric_name: str)
lmms_eval/tasks/kris_bench/utils.py:709
↓ 4 callersFunction_aggregate_table_teds
Weighted average of table TEDS across pages.
lmms_eval/tasks/omnidocbench/utils.py:752
↓ 4 callersFunction_aggregate_text_edit
Weighted average of text edit distances across pages.
lmms_eval/tasks/omnidocbench/utils.py:720
↓ 4 callersFunction_build_prompt_text
Build the full prompt text from document fields.
lmms_eval/tasks/mmsi_video/utils.py:244
↓ 4 callersFunction_build_scene_prompt
Build scene prompt matching original codebase format. Options list mixes shape candidates + scene candidates (simple + complex). task_typ
lmms_eval/tasks/unig2u/illusionbench/arshia_utils.py:258
↓ 4 callersFunction_coerce_bool
(value: Any)
lmms_eval/tasks/viverbench/utils.py:12
↓ 4 callersMethod_compute_sample_indices
( self, total_frames: int, original_fps: float, start_frame: int = 0,
lmms_eval/models/simple/tempo.py:165
↓ 4 callersFunction_dedupe
(items)
lmms_eval/tasks/_task_utils/media_resolver.py:9
↓ 4 callersFunction_encode_pil_image_to_bytes
(image: Image.Image, *, image_format: str, quality: Optional[int])
lmms_eval/models/model_utils/media_encoder.py:69
↓ 4 callersMethod_extract_image
Extract PIL Image from various formats.
lmms_eval/models/simple/ovis_u1.py:245
← previousnext →101–200 of 7,449, ranked by callers