Functions — github.com/Fanziyang-v/FlashVID

hub / github.com/Fanziyang-v/FlashVID / functions

Functions6,334 in github.com/Fanziyang-v/FlashVID

⨍ Functions 6,334◇ Types & classes 572↳ Endpoints 36

↓ 4 callersFunctionfloatify

(num: str)

lmms-eval/lmms_eval/tasks/megabench/metrics/scoring/general_numerical_match.py:138

↓ 4 callersMethodforward_features

(self, x, return_all_features=False)

llava/model/multimodal_encoder/dev_eva_clip/eva_clip/eva_vit_model.py:529

↓ 4 callersMethodfrom_string

(cls, s)

lmms-eval/lmms_eval/tasks/megabench/metrics/metric_type.py:188

↓ 4 callersMethodget_config

(self, key: str)

lmms-eval/lmms_eval/api/task.py:1631

↓ 4 callersFunctionget_file_datetime

Given the results and sample results filenames, extracts and returns the datetime.

lmms-eval/lmms_eval/utils.py:316

↓ 4 callersFunctionget_metric_aggregation

(name)

lmms-eval/lmms_eval/api/registry.py:151

↓ 4 callersMethodget_metrics

(self, gt_answers, preds)

lmms-eval/lmms_eval/tasks/multidocvqa/utils.py:70

↓ 4 callersFunctionget_pretrained_cfg

(model: str, tag: str)

llava/model/multimodal_encoder/dev_eva_clip/eva_clip/pretrained.py:210

↓ 4 callersMethodget_prompt

(self)

llava/conversation.py:47

↓ 4 callersFunctionget_rerank_incontext_example

(rerank_num)

lmms-eval/lmms_eval/tasks/mmsearch/utils/prompt_utils.py:25

↓ 4 callersMethodget_response_from_cache

Get the response from the cache

lmms-eval/lmms_eval/api/model.py:208

↓ 4 callersFunctionget_scores

Calculate various scores based on the given results. Args: scores (dict or list): A dictionary or list containing results where each

lmms-eval/lmms_eval/tasks/camerabench_vqa/utils.py:9

↓ 4 callersFunctionget_scores

Calculate various scores based on the given results. Args: scores (dict or list): A dictionary or list containing results where each

lmms-eval/lmms_eval/tasks/naturalbench/utils.py:9

↓ 4 callersMethodhas_test_docs

Whether the task has a test set

lmms-eval/lmms_eval/api/task.py:306

↓ 4 callersMethodhas_test_docs

(self)

lmms-eval/lmms_eval/api/task.py:1091

↓ 4 callersMethodhas_validation_docs

Whether the task has a validation set

lmms-eval/lmms_eval/api/task.py:301

↓ 4 callersMethodhas_validation_docs

(self)

lmms-eval/lmms_eval/api/task.py:1085

↓ 4 callersFunctionhash_string

(string: str)

lmms-eval/lmms_eval/utils.py:57

↓ 4 callersFunctionis_higher_better

(metric_name)

lmms-eval/lmms_eval/api/registry.py:160

↓ 4 callersFunctionis_non_str_iterable

(obj)

lmms-eval/lmms_eval/api/metrics.py:460

↓ 4 callersFunctionllava_aggregation

(results, category)

lmms-eval/lmms_eval/tasks/llava-in-the-wild/utils.py:114

↓ 4 callersFunctionllava_aggregation

(results, category)

lmms-eval/lmms_eval/tasks/llava-in-the-wild/utils_ko.py:161

↓ 4 callersFunctionllava_aggregation

(results, category)

lmms-eval/lmms_eval/tasks/multilingual-llava-bench-in-the-wild/utils.py:151

↓ 4 callersFunctionllava_aggregation

(results, category)

lmms-eval/lmms_eval/tasks/llava-bench-coco/utils.py:162

↓ 4 callersMethodload_cache

(self)

lmms-eval/lmms_eval/api/model.py:107

↓ 4 callersMethodload_model

(self)

llava/model/multimodal_encoder/hf_vision.py:23

↓ 4 callersFunctionnormalize_math_notation

Normalize mathematical notation for comparison (e.g., n² -> n^2, n³ -> n^3)

lmms-eval/lmms_eval/tasks/mmvu/utils.py:134

↓ 4 callersFunctionparse

(x)

llava/model/multimodal_encoder/dev_eva_clip/eva_clip/utils.py:274

↓ 4 callersFunctionparse_choice_img

(choice: str, img_token: str)

lmms-eval/lmms_eval/tasks/seedbench_2_plus/utils.py:8

↓ 4 callersFunctionparse_choice_img

(choice: str, img_token: str)

lmms-eval/lmms_eval/tasks/seedbench_2/utils.py:8

↓ 4 callersFunctionparse_multi_choice_response

Parse the prediction from the generated response. Return the predicted index e.g., A, B, C, D.

lmms-eval/lmms_eval/tasks/visualwebbench/utils.py:223

↓ 4 callersFunctionparse_pddl_attr_from_string

( s, attr_starter="(:", attr_ender=")", inner_starter="(", inner_ender=")", overlap=Fa

lmms-eval/lmms_eval/tasks/megabench/metrics/scoring/symbolic_planning.py:43

↓ 4 callersFunctionparse_subtitle_time

(time_str)

lmms-eval/lmms_eval/tasks/egoplan/utils.py:33

↓ 4 callersFunctionparse_time

(tstr)

lmms-eval/lmms_eval/tasks/scivideobench/utils.py:23

↓ 4 callersMethodprepare_messages

Prepare messages in the format expected by the API

lmms-eval/lmms_eval/llm_judge/base.py:33

↓ 4 callersFunctionprocess_option_for_question

(sent)

lmms-eval/lmms_eval/tasks/vitatecs/utils.py:69

↓ 4 callersFunctionremove_not

(x)

lmms-eval/lmms_eval/tasks/scibench/utils.py:84

↓ 4 callersFunctionremove_sp

(text)

lmms-eval/lmms_eval/tasks/covost2/utils.py:76

↓ 4 callersFunctionremove_sp

(text, language)

lmms-eval/lmms_eval/tasks/open_asr/utils.py:65

↓ 4 callersMethodset_config

Set or update the configuration for a given key.

lmms-eval/lmms_eval/api/task.py:612

↓ 4 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/lmms_eval/utils.py:194

↓ 4 callersFunctionstr_to_iterable

Converts a string representation of an iterable to an iterable.

lmms-eval/lmms_eval/tasks/megabench/metrics/scoring/common/conversions.py:45

↓ 4 callersFunctionstr_to_set

Converts a string representation of an iterable to a set.

lmms-eval/lmms_eval/tasks/megabench/metrics/scoring/common/conversions.py:86

↓ 4 callersMethodtokenize

(self, sent: str)

lmms-eval/lmms_eval/tasks/tedlium/utils.py:117

↓ 4 callersFunctionunpad_image

Unpads a PyTorch tensor of a padded and resized image. Args: tensor (torch.Tensor): The image tensor, assumed to be in CxHxW format.

llava/model/llava_arch.py:127

↓ 4 callersFunctionverify

(s, target_sequence)

lmms-eval/lmms_eval/tasks/gedit_bench/viescore/utils.py:97

↓ 4 callersFunctionvqa_evaluation

(predict, answers)

lmms-eval/lmms_eval/tasks/ocrbench_v2/vqa_metric.py:23

↓ 4 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/lmms_eval/tasks/ocrbench_v2/TEDS_metric.py:498

↓ 3 callersMethod__init__

pass a string `regex` to run `re.compile(r"regex")` on. `fallback` defines the output returned if no matches for the regex are locate

lmms-eval/lmms_eval/filters/extraction.py:33

↓ 3 callersMethod__init__

(self, date=None, chntext=None)

lmms-eval/lmms_eval/tasks/librispeech/cn_tn.py:818

↓ 3 callersFunction_aggregate_per_category

(results)

lmms-eval/lmms_eval/tasks/salbench/utils.py:102

↓ 3 callersFunction_build_prompt

Build the textual prompt: modality instruction + question + choices + post_prompt.

lmms-eval/lmms_eval/tasks/av_speakerbench/utils.py:51

↓ 3 callersMethod_clamp_coordinates

(self, v_x1, v_y1, v_x2, v_y2)

lmms-eval/lmms_eval/models/model_utils/thyme/sandbox.py:225

↓ 3 callersFunction_compute_domain_breakdown

Helper function to compute per-domain statistics Args: results: List of dicts with 'score' and 'domain' fields metric_key: N

lmms-eval/lmms_eval/tasks/ueval/utils.py:284

↓ 3 callersMethod_create_events

(self, name: str)

playground/bench_efficiency.py:264

↓ 3 callersFunction_create_zero_result

Create a zero-score result dict

lmms-eval/lmms_eval/tasks/imgedit/utils.py:293

↓ 3 callersMethod_decode_audio

Decode an AudioDecoder object or audio dict to a standard dict format.

lmms-eval/lmms_eval/models/simple/qwen3_omni.py:179

↓ 3 callersMethod_encode_image

(self, image, image_format)

lmms-eval/lmms_eval/tasks/megabench/metrics/scoring/vlm_as_judge.py:81

↓ 3 callersMethod_extract_answer_by_rule

Robust extraction: 1) Try <answer>...<\answer> (case-insensitive, flexible whitespace) 2) If not found, try to extract last n

lmms-eval/lmms_eval/tasks/seephys/seephys_evals.py:258

↓ 3 callersFunction_extract_consistency_score_and_reason

(response: str)

lmms-eval/lmms_eval/tasks/kris_bench/utils.py:378

↓ 3 callersFunction_extract_score_and_reason

(response: str, *, score_key: str, reason_fields: List[str], prefix_patterns: Optional[List[str]] = None)

lmms-eval/lmms_eval/tasks/kris_bench/utils.py:365

↓ 3 callersFunction_get_choices

(doc: Dict)

lmms-eval/lmms_eval/tasks/super_gpqa/utils.py:9

↓ 3 callersMethod_get_tasklist

(self, name)

lmms-eval/lmms_eval/tasks/__init__.py:216

↓ 3 callersFunction_get_video_file

(prefix: str, video_name: str, suffix: str)

lmms-eval/lmms_eval/tasks/_task_utils/video_loader.py:12

↓ 3 callersMethod_name_is_tag

(self, name)

lmms-eval/lmms_eval/tasks/__init__.py:172

↓ 3 callersFunction_normalize_score

Normalize a 1..max_score score to a 0..100 scale (matching summarize.py).

lmms-eval/lmms_eval/tasks/kris_bench/utils.py:70

↓ 3 callersMethod_parse

Try to parse a single answer.

lmms-eval/lmms_eval/tasks/megabench/metrics/parsing/answer_str_parse.py:18

↓ 3 callersFunction_process_text_and_mixed_media

Process the text prompt and the input medias when the media files contain both image and video. In this case, sample frames from the video an

lmms-eval/lmms_eval/tasks/megabench/image_video_utils.py:101

↓ 3 callersFunction_sacreformat

Format refs and preds for sacrebleu corpus calculation. It is very particular

lmms-eval/lmms_eval/api/metrics.py:464

↓ 3 callersMethodapply

(self, resps, docs)

lmms-eval/lmms_eval/tasks/worldqa/utils.py:250

↓ 3 callersMethodattention

(self, x: torch.Tensor, attn_mask: Optional[torch.Tensor] = None)

llava/model/multimodal_encoder/dev_eva_clip/eva_clip/transformer.py:442

↓ 3 callersFunctionbuild_filter_ensemble

Create a filtering pipeline.

lmms-eval/lmms_eval/filters/__init__.py:29

↓ 3 callersFunctionbuild_prompt

(doc, index)

lmms-eval/lmms_eval/tasks/ovobench/utils.py:37

↓ 3 callersFunctionbuild_transform

(input_size)

lmms-eval/lmms_eval/models/simple/internvl2.py:30

↓ 3 callersFunctioncalculate_image_score

(result)

lmms-eval/lmms_eval/tasks/camerabench_vqa/utils.py:38

↓ 3 callersFunctioncalculate_image_score

(result)

lmms-eval/lmms_eval/tasks/naturalbench/utils.py:38

↓ 3 callersFunctioncalculate_question_score

(result)

lmms-eval/lmms_eval/tasks/camerabench_vqa/utils.py:52

↓ 3 callersFunctioncalculate_question_score

(result)

lmms-eval/lmms_eval/tasks/naturalbench/utils.py:52

↓ 3 callersFunctioncall_judge_with_retry

Calls the OpenAI API's chat completion endpoint with exponential backoff.

lmms-eval/lmms_eval/tasks/plm_videobench/eval_utils.py:201

↓ 3 callersMethodcan_infer

(self, answer, choices, question_type=None, valid_option=None)

lmms-eval/lmms_eval/tasks/mmupd/mmupd_evals.py:392

↓ 3 callersMethodcan_infer

(self, answer, choices)

lmms-eval/lmms_eval/tasks/mmbench/mmbench_evals.py:121

↓ 3 callersFunctioncapability_aggregate_results

Args: results: a list of values returned by process_results Returns: A score

lmms-eval/lmms_eval/tasks/capability/utils.py:121

↓ 3 callersFunctioncompute_flops

Compute the FLOPs for a transformer model. Args: D (int): Dimension of the model. S (int): Sequence length. L (int):

tools/flops/llava_vid.py:3

↓ 3 callersFunctioncompute_flops

Compute the FLOPs for a transformer model. Args: D (int): Dimension of the model. S (int): Sequence length. L (int):

tools/flops/llava_ov.py:3

↓ 3 callersFunctionconstruct_prompt

(doc, mc_prompt="", open_ended_prompt="", prompt_type="reasoning")

lmms-eval/lmms_eval/tasks/mmmu/reasoning/utils.py:44

↓ 3 callersMethodconstruct_tree_from_dict

Convert Dictionary into Tree Example: input(dict) { "menu": [

lmms-eval/lmms_eval/tasks/synthdog/donut_evaluator.py:133

↓ 3 callersFunctioncreate_graph_from_cogmap

Create a graph representation from a cognitive map. Args: cogmap: The cognitive map dictionary Returns: A directed graph (Di

lmms-eval/lmms_eval/tasks/spatialtreebench/metrics/mindcube_cogmap/src/evaluation/cogmap/graph_operations.py:16

↓ 3 callersMethoddevice

(self)

llava/model/multimodal_encoder/eva_clip/eva_vit.py:855

↓ 3 callersMethoddevice

(self)

lmms-eval/lmms_eval/models/simple/slime.py:185

↓ 3 callersMethoddevice

(self)

lmms-eval/lmms_eval/models/simple/internvideo2.py:328

↓ 3 callersMethoddevice

(self)

lmms-eval/lmms_eval/models/simple/videochat_flash.py:154

↓ 3 callersMethoddevice

(self)

lmms-eval/lmms_eval/models/simple/llava.py:185

↓ 3 callersMethoddevice

(self)

lmms-eval/lmms_eval/models/simple/llava_onevision_moviechat.py:246

↓ 3 callersMethoddevice

(self)

lmms-eval/lmms_eval/models/simple/llava_onevision.py:269

↓ 3 callersMethoddevice

(self)

lmms-eval/lmms_eval/models/simple/oryx.py:187

↓ 3 callersMethoddevice

(self)

lmms-eval/lmms_eval/models/simple/ross.py:185

↓ 3 callersMethoddevice

(self)

lmms-eval/lmms_eval/models/simple/internvl2.py:288

↓ 3 callersMethoddevice

(self)

lmms-eval/lmms_eval/models/simple/xcomposer2_4KHD.py:119

↓ 3 callersMethoddevice

(self)

lmms-eval/lmms_eval/models/simple/moviechat.py:215

↓ 3 callersMethoddevice

(self)

lmms-eval/lmms_eval/models/simple/llama_vid.py:265

← previous next →201–300 of 6,334, ranked by callers