MCPcopy Create free account

hub / github.com/Alpha-VLLM/Lumina-DiMOO / functions

Functions3,694 in github.com/Alpha-VLLM/Lumina-DiMOO

⨍ Functions 3,694◇ Types & classes 675
↓ 3 callersFunctiongenerate_crop_size_list
(num_patches, patch_size, max_ratio=4.0)
VLMEvalKit/vlmeval/vlm/lumina_dimmo/image_utils.py:41
↓ 3 callersMethodgenerate_vanilla
(self, image_path, text)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2_4KHD.py:138
↓ 3 callersMethodgenerate_vanilla
(self, image_path, text)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2.py:117
↓ 3 callersMethodgenerate_vanilla
(self, image_path, text)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2d5.py:298
↓ 3 callersFunctionget_causal_attention_bias
(cache: BufferCache, seq_len: int, device: torch.device)
model/modeling_llada.py:501
↓ 3 callersFunctionget_causal_attention_bias
(cache: BufferCache, seq_len: int, device: torch.device)
VLMEvalKit/vlmeval/vlm/lumina_dimmo/modeling_llada.py:494
↓ 3 callersFunctionget_gt_pred_lines
(gt_items, pred_items, line_type)
VLMEvalKit/vlmeval/dataset/Omnidocbench/utils.py:819
↓ 3 callersMethodget_index
(self, bound, fps, max_frame, first_idx=0)
VLMEvalKit/vlmeval/dataset/mvbench.py:200
↓ 3 callersMethodget_index
(self, bound, fps, max_frame, first_idx=0)
VLMEvalKit/vlmeval/dataset/tamperbench.py:222
↓ 3 callersFunctionget_intersection
(pD,pG)
VLMEvalKit/vlmeval/dataset/utils/Ocrbench_v2/spotting_eval/script.py:130
↓ 3 callersMethodget_model
(self)
VLMEvalKit/vlmeval/vlm/hawk_vl/hawk/model/hawk_arch.py:48
↓ 3 callersMethodget_multiplier
(self, unit)
VLMEvalKit/vlmeval/dataset/image_vqa.py:1736
↓ 3 callersMethodget_output_embeddings
(self)
VLMEvalKit/vlmeval/vlm/lumina_dimmo/modeling_llada.py:1476
↓ 3 callersFunctionget_single_answer_type_text
(answer_type, is_chinese)
VLMEvalKit/vlmeval/dataset/utils/olympiadbench.py:34
↓ 3 callersMethodget_sorted_text_list
(self, selected_annos)
VLMEvalKit/vlmeval/dataset/Omnidocbench/omnidocbench.py:175
↓ 3 callersMethodget_subtitles
(self, subtitle_path, frame_indices=None, fps=None, sub_time=False)
VLMEvalKit/vlmeval/dataset/cgbench.py:519
↓ 3 callersMethodget_subtitles
(self, subtitle_path, frame_indices=None, fps=None, sub_time=False)
VLMEvalKit/vlmeval/dataset/cgbench.py:1399
↓ 3 callersFunctionget_timestampes
(frame_indices, fps)
VLMEvalKit/vlmeval/dataset/CGAVCounting/utils.py:39
↓ 3 callersFunctionhas_word
(sentence, word)
VLMEvalKit/vlmeval/dataset/utils/mmniah.py:5
↓ 3 callersMethodinfer_data
( self, data_sample, system=' ', question_prompt='', # add in the end of question ans
VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:304
↓ 3 callersMethodinit_cache
(self)
model/modeling_llada.py:593
↓ 3 callersFunctionis_float
(val)
VLMEvalKit/vlmeval/dataset/utils/Ocrbench_v2/TEDS_metric.py:592
↓ 3 callersFunctionjaccard_index
Calculate the Jaccard Index.
VLMEvalKit/vlmeval/dataset/utils/megabench/scoring/common/metrics.py:65
↓ 3 callersMethodload_data
(self,eval_file,gt_file,pred_key,gt_key)
VLMEvalKit/vlmeval/dataset/Omnidocbench/omnidocbench.py:433
↓ 3 callersFunctionmake_input
(prompt, question_content)
VLMEvalKit/vlmeval/dataset/utils/olympiadbench.py:86
↓ 3 callersFunctionmaybe_zero_3
(param, ignore_status=False, name=None)
VLMEvalKit/vlmeval/vlm/ola/ola/utils.py:107
↓ 3 callersFunctionmpo_post_processing
(response, dataset)
VLMEvalKit/vlmeval/vlm/internvl/utils.py:246
↓ 3 callersFunctionmse
Return the mean squared error.
VLMEvalKit/vlmeval/dataset/utils/megabench/scoring/common/metrics.py:89
↓ 3 callersFunctionparse_answer
(answer, answer_type="multiple choice")
VLMEvalKit/vlmeval/dataset/dynamath.py:35
↓ 3 callersFunctionparse_json
Parse the JSON object, including nested JSON strings.
VLMEvalKit/vlmeval/dataset/utils/megabench/parsing/common/parsers.py:12
↓ 3 callersFunctionparse_outer_inner_str
(s, str_ender, inner_starter, inner_ender)
VLMEvalKit/vlmeval/dataset/utils/megabench/scoring/symbolic_planning.py:25
↓ 3 callersFunctionphones_for_word
A wrapper for pronouncingpy's phones_for_word to handle out-of-vocab issues.
VLMEvalKit/vlmeval/dataset/utils/megabench/scoring/constrained_generation.py:69
↓ 3 callersFunctionpost_check
(line, prefetch=False)
VLMEvalKit/vlmeval/dataset/utils/mathvista.py:74
↓ 3 callersFunctionpost_check
(line, prefetch=False)
VLMEvalKit/vlmeval/dataset/utils/ocr_reasoning.py:68
↓ 3 callersFunctionpost_check
(line, prefetch=False)
VLMEvalKit/vlmeval/dataset/utils/mathv.py:104
↓ 3 callersFunctionprefetch_circular_group
(sub_data, verbose=False)
VLMEvalKit/vlmeval/dataset/utils/multiple_choice.py:364
↓ 3 callersFunctionprocess_triplets
(triplets)
VLMEvalKit/vlmeval/dataset/utils/Ocrbench_v2/TEDS_metric.py:690
↓ 3 callersFunctionpromote_param_to_fp32
(param: nn.Parameter)
xllmx/util/tensor_type.py:5
↓ 3 callersMethodread_video
(self, video_path, bound=None)
VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:230
↓ 3 callersFunctionreorganize_prompt
(message, image_num, dataset=None)
VLMEvalKit/vlmeval/vlm/sail_vl.py:176
↓ 3 callersMethodsave_video_frames
(self, video, uid, num_frames=8, fps=-1)
VLMEvalKit/vlmeval/dataset/CGAVCounting/cg_av_counting.py:300
↓ 3 callersMethodset_activation_checkpointing
(self, strategy: Optional[ActivationCheckpointingStrategy])
VLMEvalKit/vlmeval/vlm/lumina_dimmo/modeling_llada.py:603
↓ 3 callersMethodset_dump_image
(self, dump_image_func)
VLMEvalKit/vlmeval/api/base.py:295
↓ 3 callersFunctionset_relevance_score
Calculate the relevance score.
VLMEvalKit/vlmeval/dataset/utils/megabench/scoring/common/metrics.py:43
↓ 3 callersFunctionsetup_seed
Set random seed
utils/generation_utils.py:84
↓ 3 callersMethodtie_weights
(self)
VLMEvalKit/vlmeval/vlm/lumina_dimmo/modeling_llada.py:1488
↓ 3 callersFunctiontime_limit
(seconds: float)
VLMEvalKit/vlmeval/dataset/utils/bmmr_grade.py:397
↓ 3 callersFunctiontokenizer_speech_token
(prompt, tokenizer, speech_token_index=SPEECH_TOKEN_INDEX, return_tensors=None)
VLMEvalKit/vlmeval/vlm/ola/ola/datasets/preprocess.py:19
↓ 3 callersFunctionvtln_warp_mel_freq
r""" Args: vtln_low_cutoff (float): Lower frequency cutoffs for VTLN vtln_high_cutoff (float): Upper frequency cutoffs for VTLN
VLMEvalKit/vlmeval/vlm/ola/ola/model/speech_encoder/beats/kaldi.py:409
↓ 3 callersFunctionxlsx2json
(xlsx_file, json_file)
VLMEvalKit/vlmeval/dataset/utils/vcrbench/cau_acc.py:8
↓ 2 callersFunctionEVAL
(dataset_name, data_file, **kwargs)
VLMEvalKit/vlmeval/tools.py:412
↓ 2 callersFunctionHD_transform
(img, im_num=36, id_scale=1.5)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2d5.py:65
↓ 2 callersFunctionICE_builder
(ICEs)
VLMEvalKit/vlmeval/dataset/utils/shortqa.py:228
↓ 2 callersFunctionMISSING
(lvl)
VLMEvalKit/vlmeval/tools.py:178
↓ 2 callersFunctionRUN
(lvl, model)
VLMEvalKit/vlmeval/tools.py:353
↓ 2 callersFunctionVisuLogic_acc
(result_file)
VLMEvalKit/vlmeval/dataset/utils/visulogic.py:94
↓ 2 callersFunctionYOrN_Extraction
(output)
VLMEvalKit/vlmeval/dataset/utils/yorn.py:226
↓ 2 callersMethod__init__
(self, dataset='MLVU', nframe=0, fps=-1)
VLMEvalKit/vlmeval/dataset/mlvu.py:23
↓ 2 callersMethod__init__
(self, dataset='QBench_Video', nframe=0, fps=-1)
VLMEvalKit/vlmeval/dataset/qbench_video.py:24
↓ 2 callersMethod__init__
(self)
VLMEvalKit/vlmeval/dataset/utils/vgrpbench/puzzles/kakuro.py:11
↓ 2 callersMethod__init__
(self)
VLMEvalKit/vlmeval/dataset/utils/vgrpbench/puzzles/thermometers.py:13
↓ 2 callersMethod__init__
(self, size: int)
VLMEvalKit/vlmeval/dataset/utils/vgrpbench/puzzles/aquarium.py:93
↓ 2 callersMethod__init__
(self, config: Qwen2Config)
VLMEvalKit/vlmeval/vlm/hawk_vl/hawk/model/language_model/hawk_qwen.py:41
↓ 2 callersMethod__init__
(self)
VLMEvalKit/vlmeval/vlm/ola/ola/model/speech_encoder/beats/modules.py:44
↓ 2 callersMethod__init__
(self, args)
VLMEvalKit/vlmeval/vlm/ola/ola/model/speech_encoder/beats/backbone.py:27
↓ 2 callersMethod__init__
(self, in_channels, out_channels, twoview=False)
VLMEvalKit/vlmeval/vlm/ola/ola/model/multimodal_projector/builder.py:45
↓ 2 callersMethod__init__
( self, vision_config=None, aligner_config=None, text_config=None, ign
VLMEvalKit/vlmeval/vlm/ursa/ursa_model/configuration_ursa.py:67
↓ 2 callersMethod__init__
(self, n_selection=16, visual_encoder_name_or_path="google/siglip-so400m-patch14-384", device="cuda")
VLMEvalKit/vlmeval/vlm/ovis/utils/mdp3.py:90
↓ 2 callersMethod_build_metric
Given a string for the metric (e.g. 'gpt_4o_as_judge'), return the actual MetricType or a specialized metric class.
VLMEvalKit/vlmeval/dataset/utils/megabench/evaluator.py:335
↓ 2 callersMethod_check_line_hints
(self, line, hints)
VLMEvalKit/vlmeval/dataset/utils/vgrpbench/puzzles/nonogram.py:11
↓ 2 callersMethod_collect_annotations
(self)
xllmx/data/dataset.py:47
↓ 2 callersFunction_convert_to_hashable
将不可哈希的类型转换为可哈希类型
VLMEvalKit/vlmeval/dataset/utils/megabench/scoring/set_equality.py:4
↓ 2 callersMethod_evaluate_field
Compute score for a single field using the given metric.
VLMEvalKit/vlmeval/dataset/utils/megabench/evaluator.py:231
↓ 2 callersFunction_extract_core_eq
(expr: str)
VLMEvalKit/vlmeval/dataset/utils/physics_eval_utils.py:53
↓ 2 callersMethod_get_chart_types
(self, code_file)
VLMEvalKit/vlmeval/dataset/utils/chartmimic/evaluator/chart_type_evaluator.py:36
↓ 2 callersFunction_get_log_energy
r"""Returns the log energy of size (m) for a strided_input (m,*)
VLMEvalKit/vlmeval/vlm/ola/ola/model/speech_encoder/beats/kaldi.py:116
↓ 2 callersFunction_get_waveform_and_window_properties
r"""Gets the waveform and window properties
VLMEvalKit/vlmeval/vlm/ola/ola/model/speech_encoder/beats/kaldi.py:125
↓ 2 callersFunction_get_window
r"""Gets a window and its log energy Returns: (Tensor, Tensor): strided_input of size (m, ``padded_window_size``) and signal_log_energy o
VLMEvalKit/vlmeval/vlm/ola/ola/model/speech_encoder/beats/kaldi.py:154
↓ 2 callersFunction_load_hf
Load the HF dataset for the given subset name.
VLMEvalKit/vlmeval/dataset/utils/megabench/tools/analysis_utils.py:9
↓ 2 callersMethod_log_colors
Get text objects of the code
VLMEvalKit/vlmeval/dataset/utils/chartmimic/evaluator/color_evaluator.py:86
↓ 2 callersMethod_log_layouts
Get objects of the code
VLMEvalKit/vlmeval/dataset/utils/chartmimic/evaluator/layout_evaluator.py:32
↓ 2 callersMethod_log_legends
Get legend objects of the code
VLMEvalKit/vlmeval/dataset/utils/chartmimic/evaluator/grid_evaluator.py:32
↓ 2 callersMethod_log_legends
Get legend objects of the code
VLMEvalKit/vlmeval/dataset/utils/chartmimic/evaluator/legend_evaluator.py:33
↓ 2 callersMethod_log_texts
Get text objects of the code
VLMEvalKit/vlmeval/dataset/utils/chartmimic/evaluator/text_evaluator.py:35
↓ 2 callersFunction_parse
(s)
VLMEvalKit/vlmeval/dataset/utils/bmmr_grade.py:326
↓ 2 callersMethod_pos_embed
(self, x: torch.Tensor)
VLMEvalKit/vlmeval/vlm/ursa/ursa_model/siglip_vit.py:476
↓ 2 callersMethod_prepare_content
inputs list[dict[str, str]], each dict has keys: ['type', 'value']
VLMEvalKit/vlmeval/vlm/qwen2_vl/model.py:297
↓ 2 callersFunction_preprocess_latex
(string: str)
VLMEvalKit/vlmeval/dataset/utils/physics_eval_utils.py:61
↓ 2 callersMethod_process
(self, formatted_messages, formatted_images)
VLMEvalKit/vlmeval/vlm/idefics.py:86
↓ 2 callersMethod_resize_image
(self, image)
VLMEvalKit/vlmeval/dataset/utils/megabench/scoring/vlm_as_judge.py:73
↓ 2 callersMethod_rgba_to_rgb
(image)
VLMEvalKit/vlmeval/dataset/utils/megabench/scoring/vlm_as_judge.py:69
↓ 2 callersFunction_standardize_expr
(expr)
VLMEvalKit/vlmeval/dataset/utils/physics_eval_utils.py:71
↓ 2 callersFunction_to_float
(text: str)
VLMEvalKit/vlmeval/dataset/utils/vqa_eval.py:194
↓ 2 callersFunctionaccuracy_evaluate_steps
(json, steps, nodes)
VLMEvalKit/vlmeval/dataset/utils/wemath.py:248
↓ 2 callersFunctionaccuracy_process_steps_data
(df, steps)
VLMEvalKit/vlmeval/dataset/utils/wemath.py:267
↓ 2 callersFunctionanls_compute
(groundtruth, prediction)
VLMEvalKit/vlmeval/dataset/utils/vqa_eval.py:230
↓ 2 callersMethodanswer
(self, conv, model, img_list, do_sample=True, max_new_tokens=500, num_beams=1, min_length=1, top_p=0.9,
VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:271
↓ 2 callersMethodapply_rotary_pos_emb
(self, pos_sin: torch.Tensor, pos_cos: torch.Tensor, t: torch.Tensor)
VLMEvalKit/vlmeval/vlm/lumina_dimmo/modeling_llada.py:408
↓ 2 callersFunctionapproximate
Return an approximation of the original string.
VLMEvalKit/vlmeval/dataset/utils/megabench/scoring/near_str_match.py:6
↓ 2 callersFunctionascii_text_to_image
Convert ASCII text into an image.
VLMEvalKit/vlmeval/dataset/utils/megabench/scoring/common/conversions.py:198
← previousnext →301–400 of 3,694, ranked by callers