MCPcopy Create free account

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

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

⨍ Functions 6,334◇ Types & classes 572↳ Endpoints 36
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/video_salmonn_2.py:131
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/internvideo2_5.py:252
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/llava_vid.py:322
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/egogpt.py:206
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/video_llava.py:143
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/qwen2_5_vl_interleave.py:161
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/qwen2_5_omni.py:134
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/mplug_owl_video.py:137
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/qwen2_audio.py:143
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/qwen3_omni.py:137
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/mantis.py:185
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/internvl.py:374
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/longva.py:227
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/vila.py:179
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/video_chatgpt.py:196
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/whisper.py:110
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/tinyllava.py:160
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/vita.py:181
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/videochat2.py:295
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/videollama3.py:132
↓ 3 callersMethoddevice
Return the device.
lmms-eval/lmms_eval/models/simple/internvl3.py:347
↓ 3 callersMethoddevice
(self)
lmms-eval/lmms_eval/models/simple/xcomposer2d5.py:119
↓ 3 callersFunctiondownload_pretrained
( cfg: Dict, force_hf_hub: bool = False, cache_dir: Union[str, None] = None, )
llava/model/multimodal_encoder/dev_eva_clip/eva_clip/pretrained.py:286
↓ 3 callersFunctiondraw_bounding_boxes
Helper function to draw bounding boxes on video frames.
lmms-eval/lmms_eval/tasks/plm_videobench/eval_utils.py:273
↓ 3 callersFunctiondynamic_preprocess
(image, min_num=1, max_num=6, image_size=448, use_thumbnail=False)
lmms-eval/lmms_eval/models/simple/internvl2.py:59
↓ 3 callersMethodevaluate
Evaluate the given request and return a response Args: request: JudgeRequest containing the evaluation context
lmms-eval/lmms_eval/llm_judge/base.py:16
↓ 3 callersMethodevaluate
(self, image_prompts, text_prompt, extract_overall_score_only=False, extract_all_score=True, echo_output=False
lmms-eval/lmms_eval/tasks/gedit_bench/viescore/__init__.py:39
↓ 3 callersFunctionevaluate_as_string
(s)
lmms-eval/lmms_eval/tasks/megabench/metrics/parsing/common/utils.py:137
↓ 3 callersFunctionextract_answer_yn
(response)
lmms-eval/lmms_eval/tasks/voicebench/utils.py:756
↓ 3 callersFunctionextract_choice_letter
(text: str)
playground/bench_efficiency.py:122
↓ 3 callersFunctionextract_code_block_content
( response, code_type=None, is_ascii_art: bool = False, should_remove_surrounding_whitespace=T
lmms-eval/lmms_eval/tasks/megabench/metrics/parsing/common/utils.py:5
↓ 3 callersFunctionextract_position
Extract and validate position data. Args: position: The position value Returns: A tuple of (x, y) coordinates
lmms-eval/lmms_eval/tasks/spatialtreebench/metrics/mindcube_cogmap/src/evaluation/cogmap/graph_operations.py:104
↓ 3 callersFunctionfastv_prune
( hidden_states: torch.Tensor, causal_mask: Optional[torch.Tensor], attentions: Optional[torch.Ten
flashvid/utils.py:404
↓ 3 callersMethodfeature_select
(self, image_forward_outs)
llava/model/multimodal_encoder/mlcd_encoder.py:51
↓ 3 callersMethodfeature_select
(self, image_forward_outs)
llava/model/multimodal_encoder/clip_encoder.py:46
↓ 3 callersMethodfetch_lexeme
(self)
lmms-eval/lmms_eval/tasks/mmsearch/retrieve_content/tokenization/tokenizers.py:24
↓ 3 callersFunctionflashvid_compression
( video_features: torch.Tensor, cls_attention: torch.Tensor, flashvid_config: FlashVidConfig, )
flashvid/utils.py:23
↓ 3 callersMethodflatten
(self, input)
lmms-eval/lmms_eval/models/simple/vllm.py:288
↓ 3 callersMethodflatten
(self, input)
lmms-eval/lmms_eval/models/simple/videochat2.py:432
↓ 3 callersFunctionformat_question_and_answer
(doc)
lmms-eval/lmms_eval/tasks/vitatecs/utils.py:81
↓ 3 callersMethodforward
(self, x)
llava/model/language_model/modeling_llama.py:212
↓ 3 callersFunctionfreeze_batch_norm_2d
Converts all `BatchNorm2d` and `SyncBatchNorm` layers of provided module into `FrozenBatchNorm2d`. If `module` is itself an instance of eithe
llava/model/multimodal_encoder/dev_eva_clip/eva_clip/utils.py:233
↓ 3 callersFunctionget_eval_result
(prompt, maxtry=10, sys_prompt=None)
lmms-eval/lmms_eval/tasks/tempcompass/utils.py:461
↓ 3 callersFunctionget_full_website_information
result_full: [{'title', 'snippet', 'content','screenshot_path'}]
lmms-eval/lmms_eval/tasks/mmsearch/utils/prompt_utils.py:30
↓ 3 callersFunctionget_intersection
(pD, pG)
lmms-eval/lmms_eval/tasks/ocrbench_v2/spotting_eval/script.py:131
↓ 3 callersFunctionget_model_config
(model_name)
llava/model/multimodal_encoder/dev_eva_clip/eva_clip/factory.py:70
↓ 3 callersMethodget_output_embeddings
(self)
llava/model/multimodal_resampler/qformer.py:878
↓ 3 callersMethodget_parsed_output
Get model output for the given messages. Args: messages: Messages in OpenAI chat format Returns: Mo
lmms-eval/lmms_eval/tasks/gedit_bench/viescore/openai_backend.py:123
↓ 3 callersFunctionget_result_summary
(anno, result_list, summary_key)
lmms-eval/lmms_eval/tasks/mmsearch/score/result_summary.py:23
↓ 3 callersFunctionhash_args
(attr, args)
lmms-eval/lmms_eval/api/model.py:335
↓ 3 callersFunctionhb_aggregation_result
(results, metric, args)
lmms-eval/lmms_eval/tasks/hallusion_bench/evaluate_hb.py:48
↓ 3 callersFunctionhb_aggregation_result_intern
(results, metric)
lmms-eval/lmms_eval/tasks/hallusion_bench/evaluate_hb.py:93
↓ 3 callersFunctionimage_to_base64
Encode PIL image to base64 JPEG.
lmms-eval/lmms_eval/tasks/kris_bench/utils.py:320
↓ 3 callersFunctionimage_to_base64
Convert PIL Image or image path to base64 string
lmms-eval/lmms_eval/tasks/babyvision_gen/utils.py:38
↓ 3 callersFunctionimage_transform
( image_size: int, is_train: bool, mean: Optional[Tuple[float, ...]] = None, std: Optional[Tup
llava/model/multimodal_encoder/dev_eva_clip/eva_clip/transform.py:59
↓ 3 callersFunctionis_equal
(md_ans, gt_ans)
lmms-eval/lmms_eval/tasks/stare/utils.py:234
↓ 3 callersFunctionis_equal
(md_ans, gt_ans)
lmms-eval/lmms_eval/tasks/emma/utils.py:293
↓ 3 callersFunctionis_float
(val)
lmms-eval/lmms_eval/tasks/ocrbench_v2/TEDS_metric.py:587
↓ 3 callersFunctionis_image_file
(file_path: str)
lmms-eval/lmms_eval/models/simple/cambrians.py:44
↓ 3 callersMethodis_none
(self, value)
lmms-eval/lmms_eval/tasks/mmupd/mmupd_evals.py:100
↓ 3 callersFunctionis_valid_facing
Check if a facing value is valid (one of: up, down, left, right, inner, outer). Args: facing: The facing value to check Returns:
lmms-eval/lmms_eval/tasks/spatialtreebench/metrics/mindcube_cogmap/src/evaluation/cogmap/cogmap_metrics.py:62
↓ 3 callersFunctionis_valid_position
Check if a position value is valid (a list of 2 numeric values). Args: position: The position value to check Returns: True i
lmms-eval/lmms_eval/tasks/spatialtreebench/metrics/mindcube_cogmap/src/evaluation/cogmap/cogmap_metrics.py:37
↓ 3 callersFunctionis_video_file
(file_path: str)
lmms-eval/lmms_eval/models/simple/cambrians.py:36
↓ 3 callersFunctionjaccard_index
Calculate the Jaccard Index.
lmms-eval/lmms_eval/tasks/megabench/metrics/scoring/common/metrics.py:65
↓ 3 callersMethodjudge
(self, expression1, expression2, precision=1e-8)
lmms-eval/lmms_eval/tasks/olympiadbench_mimo/olympiadbench_evals.py:74
↓ 3 callersMethodlist_all_tasks
(self, list_groups=True, list_tags=True, list_subtasks=True)
lmms-eval/lmms_eval/tasks/__init__.py:97
↓ 3 callersFunctionload_jsonl_data
Load data from a JSONL file. Args: jsonl_path: Path to the JSONL file Returns: List of loaded JSON objects
lmms-eval/lmms_eval/tasks/spatialtreebench/metrics/mindcube_cogmap/src/evaluation/core/io_utils.py:16
↓ 3 callersMethodload_model
(self, device_map=None)
llava/model/multimodal_encoder/mlcd_encoder.py:39
↓ 3 callersMethodload_model
(self, device_map=None)
llava/model/multimodal_encoder/siglip_encoder.py:563
↓ 3 callersMethodload_model
(self, device_map="auto")
llava/model/multimodal_encoder/open_clip_encoder.py:40
↓ 3 callersMethodload_model
(self, device_map=None)
llava/model/multimodal_encoder/clip_encoder.py:35
↓ 3 callersMethodload_model
(self)
llava/model/multimodal_encoder/dev_eva_clip/eva_vit.py:52
↓ 3 callersMethodload_model
(self, device_map=None)
llava/model/multimodal_encoder/eva_clip/eva_clip_encoder.py:33
↓ 3 callersFunctionload_plm_stc_metadata
(config)
lmms-eval/lmms_eval/tasks/plm_videobench/eval_utils.py:308
↓ 3 callersFunctionload_video
(video_path, max_frames, annot_sample_rate=1)
lmms-eval/lmms_eval/tasks/plm_videobench/eval_utils.py:240
↓ 3 callersMethodload_video
(self, video_path, max_frames_num)
lmms-eval/lmms_eval/models/simple/llava_onevision.py:429
↓ 3 callersMethodlock
lock modules Args: unlocked_groups (int): leave last n layer groups unlocked (default: 0)
llava/model/multimodal_encoder/dev_eva_clip/eva_clip/timm_model.py:73
↓ 3 callersFunctionlongvt_doc_to_text
(doc, lmms_eval_specific_kwargs=None)
lmms-eval/lmms_eval/tasks/longvt/utils.py:37
↓ 3 callersFunctionmean
(arr)
lmms-eval/lmms_eval/api/metrics.py:23
↓ 3 callersFunctionmmmu_doc_to_text
(doc, lmms_eval_specific_kwargs=None)
lmms-eval/lmms_eval/tasks/mmmu/reasoning/utils.py:57
↓ 3 callersFunctionmse
Return the mean squared error.
lmms-eval/lmms_eval/tasks/megabench/metrics/scoring/common/metrics.py:89
↓ 3 callersFunctionnormalize_str
(string)
lmms-eval/lmms_eval/tasks/videommmu/utils.py:443
↓ 3 callersFunctionnormalize_str
Normalize the str to lower case and make them float numbers if possible. https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445
lmms-eval/lmms_eval/tasks/jmmmu/utils.py:362
↓ 3 callersFunctionnormalize_str
Normalize the str to lower case and make them float numbers if possible. https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445
lmms-eval/lmms_eval/tasks/mmmu_pro/utils.py:394
↓ 3 callersFunctionnormalize_str
Normalize the str to lower case and make them float numbers if possible. https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445
lmms-eval/lmms_eval/tasks/mmmu_pro/reasoning/utils.py:415
↓ 3 callersFunctionnormalize_str
Normalize the str to lower case and make them float numbers if possible. https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445
lmms-eval/lmms_eval/tasks/mmmu/utils.py:495
↓ 3 callersFunctionnormalize_str
Normalize the str to lower case and make them float numbers if possible. https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445
lmms-eval/lmms_eval/tasks/mmmu/utils_group_img.py:475
↓ 3 callersFunctionnormalize_str
Normalize the str to lower case and make them float numbers if possible. https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445
lmms-eval/lmms_eval/tasks/mmmu/reasoning/utils.py:418
↓ 3 callersFunctionnormalize_str
Normalize the str to lower case and make them float numbers if possible. https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445
lmms-eval/lmms_eval/tasks/mirb/utils.py:78
↓ 3 callersFunctionpairwise_cosine_distances
Calculate pairwise cosine distances for a batch of feature vectors. Args: image_features (torch.Tensor): Visual features, of shape (bsz,
flashvid/token_selection.py:14
↓ 3 callersFunctionparse_json
Parse the JSON object, including nested JSON strings.
lmms-eval/lmms_eval/tasks/megabench/metrics/parsing/common/parsers.py:13
↓ 3 callersFunctionparse_options
(options)
lmms-eval/lmms_eval/tasks/videommmu/utils.py:120
↓ 3 callersFunctionparse_outer_inner_str
(s, str_ender, inner_starter, inner_ender)
lmms-eval/lmms_eval/tasks/megabench/metrics/scoring/symbolic_planning.py:25
↓ 3 callersFunctionpatch_target_module
( to_patch: str, replace_with, )
lmms-eval/lmms_eval/tasks/_task_utils/math_verify_utils.py:10
↓ 3 callersFunctionphones_for_word
A wrapper for pronouncingpy's phones_for_word to handle out-of-vocab issues.
lmms-eval/lmms_eval/tasks/megabench/metrics/scoring/constrained_generation.py:70
↓ 3 callersFunctionphyx_doc_to_text
(doc, lmms_eval_specific_kwargs=None)
lmms-eval/lmms_eval/tasks/phyx/reasoning/utils.py:11
↓ 3 callersFunctionpil_image_to_bytes
(pil_image, format="PNG")
lmms-eval/lmms_eval/tasks/mmsearch/utils/image_utils.py:195
↓ 3 callersFunctionprep_data
()
lmms-eval/lmms_eval/tasks/vinoground/utils.py:23
↓ 3 callersMethodprepare_prompt
Prepare prompt in OpenAI chat format. Args: image_links: Single image or list of PIL Images / image paths te
lmms-eval/lmms_eval/tasks/gedit_bench/viescore/openai_backend.py:95
↓ 3 callersMethodprocess_digit_article
(self, in_text)
lmms-eval/lmms_eval/tasks/_task_utils/vqa_eval_metric.py:193
← previousnext →301–400 of 6,334, ranked by callers