Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/VITA-MLLM/VITA
/ functions
Functions
1,650 in github.com/VITA-MLLM/VITA
⨍
Functions
1,650
◇
Types & classes
320
↳
Endpoints
1
↓ 2 callers
Function
cn_ratio
(data)
VLMEvalKit/scripts/mmb_eval_gradio.py:47
↓ 2 callers
Function
colored
(s, color)
VLMEvalKit/vlmeval/smp/misc.py:53
↓ 2 callers
Function
concat_images_vlmeval
(images, target_size=-1, mode='h', return_image=False)
VLMEvalKit/vlmeval/smp/vlm.py:26
↓ 2 callers
Method
concat_tilist
(self, message)
VLMEvalKit/vlmeval/vlm/llava/llava.py:106
↓ 2 callers
Function
count_choice
(splits, choices, prefix='', suffix='')
VLMEvalKit/vlmeval/utils/matching_util.py:23
↓ 2 callers
Function
decode_base64_to_image
(base64_string, target_size=-1)
VLMEvalKit/vlmeval/smp/vlm.py:101
↓ 2 callers
Function
dynamic_preprocess
(image, min_num=1, max_num=12, image_size=448, use_thumbnail=True)
data_tools/concat_data_patch.py:35
↓ 2 callers
Function
edit_config
(repo_id)
VLMEvalKit/vlmeval/vlm/yi_vl.py:28
↓ 2 callers
Method
encode_images
(self, images)
vita/model/vita_arch.py:160
↓ 2 callers
Method
evaluate
(self, eval_file, **judge_kwargs)
VLMEvalKit/vlmeval/dataset/dude.py:163
↓ 2 callers
Function
extract_answer_from_item
(model, item, dataset_name=None)
VLMEvalKit/vlmeval/dataset/utils/multiple_choice.py:237
↓ 2 callers
Method
feature_select
(self, image_forward_outs)
vita/model/multimodal_encoder/clip/clip_encoder.py:27
↓ 2 callers
Method
feature_select
(self, image_forward_outs)
vita/model/multimodal_encoder/internvit/internvit_encoder.py:34
↓ 2 callers
Method
fill_fix_offset
(more_fix_crop, image_w, image_h, crop_w, crop_h)
VLMEvalKit/vlmeval/dataset/utils/mvbench.py:316
↓ 2 callers
Function
fintabnet_normalize
(s)
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:162
↓ 2 callers
Method
flush
(self)
vita/util/utils.py:96
↓ 2 callers
Method
forward_features
(self, x, return_all_features=False)
vita/model/multimodal_encoder/eva_clip/eva_vit.py:763
↓ 2 callers
Method
generate
( self, inputs: Optional[torch.Tensor] = None, images: Optional[torch.Tensor] = None,
vita/model/language_model/vita_qwen2.py:185
↓ 2 callers
Method
generate
(self, inputs, **kwargs)
VLMEvalKit/vlmeval/api/hf_chat_model.py:241
↓ 2 callers
Method
generate_inner
The inner function to generate the answer. Returns: tuple(int, str, str): ret_code, response, log
VLMEvalKit/vlmeval/api/base.py:47
↓ 2 callers
Method
generate_vanilla
(self, image_path, prompt)
VLMEvalKit/vlmeval/vlm/monkey.py:23
↓ 2 callers
Method
generate_vanilla
(self, image_path, prompt)
VLMEvalKit/vlmeval/vlm/monkey.py:105
↓ 2 callers
Method
get_input_embeddings
(self, input_ids: torch.Tensor)
web_demo/vllm_tools/vllm_file/qwen2.py:600
↓ 2 callers
Function
get_mm_adapter_state_maybe_zero_3
(named_params, keys_to_match)
vita/train/vita_trainer.py:32
↓ 2 callers
Function
get_precision
(gt_ans: float)
VLMEvalKit/vlmeval/dataset/mmlongbench.py:113
↓ 2 callers
Method
initialize_audio_modules
(self, model_args)
vita/model/vita_arch.py:71
↓ 2 callers
Method
initialize_vision_modules
(self, model_args)
vita/model/vita_arch.py:38
↓ 2 callers
Function
is_exact_match
(s)
VLMEvalKit/vlmeval/dataset/mmlongbench.py:159
↓ 2 callers
Function
is_large
(x)
VLMEvalKit/scripts/auto_run.py:14
↓ 2 callers
Method
kv_cache_prefix_forward
(self, prefix, prefix_lens, past_key_values)
vita/model/vita_tts/decoder/decoder.py:127
↓ 2 callers
Function
levenshtein_distance
(s1, s2)
VLMEvalKit/vlmeval/dataset/utils/vqa_eval.py:214
↓ 2 callers
Function
load_video
(video_path, image_processor, num_frames=MAX_IMAGE_LENGTH, image_aspect_ratio='square')
videomme/yt_video_inference_qa_imgs.py:122
↓ 2 callers
Function
load_video
(video_path)
VLMEvalKit/vlmeval/vlm/video_llm/llama_vid.py:14
↓ 2 callers
Function
localize_df
(data, dname, nproc=32)
VLMEvalKit/vlmeval/smp/file.py:34
↓ 2 callers
Method
match
Return True if the value matches the other value. Args: other (Value) Returns: a boolean
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:246
↓ 2 callers
Function
mcq_circular_eval
(model, data, meta, nproc, result_file, dataset_name=None)
VLMEvalKit/vlmeval/dataset/utils/multiple_choice.py:375
↓ 2 callers
Function
mmqa_display
(question, target_size=512)
VLMEvalKit/vlmeval/smp/vlm.py:57
↓ 2 callers
Method
normalize
( self, input_features: List[np.ndarray], attention_mask: Optional[np.ndarray] = None )
web_demo/vllm_tools/qwen2p5_model_weight_file/processor_whale.py:235
↓ 2 callers
Function
okn
(o, n=4)
VLMEvalKit/vlmeval/tools.py:163
↓ 2 callers
Function
parse_require_file
(fpath)
VLMEvalKit/setup.py:57
↓ 2 callers
Method
pre_nn_forward
(self, hidden, hidden_lens)
vita/model/vita_tts/decoder/decoder.py:162
↓ 2 callers
Function
prefetch_circular_group
(sub_data, verbose=False)
VLMEvalKit/vlmeval/dataset/utils/multiple_choice.py:275
↓ 2 callers
Method
prepare_itlist
(self, inputs)
VLMEvalKit/vlmeval/api/claude.py:44
↓ 2 callers
Method
prepare_itlist
(self, inputs)
VLMEvalKit/vlmeval/api/hunyuan.py:67
↓ 2 callers
Method
prepare_itlist
(self, inputs)
VLMEvalKit/vlmeval/api/gpt.py:133
↓ 2 callers
Method
prepare_itlist
(self, inputs)
VLMEvalKit/vlmeval/api/qwen_vl_api.py:40
↓ 2 callers
Method
preproc_content
Convert the raw input messages to a list of dicts. Args: inputs: raw input messages. Returns: list(dict): Th
VLMEvalKit/vlmeval/vlm/base.py:64
↓ 2 callers
Method
preproc_content
Convert the raw input messages to a list of dicts. Args: inputs: raw input messages. Returns: list(dict): Th
VLMEvalKit/vlmeval/api/base.py:104
↓ 2 callers
Method
process
(self, image, question)
VLMEvalKit/vlmeval/vlm/cambrian.py:51
↓ 2 callers
Method
process_answer_prefix
(self, answer, prefixes)
VLMEvalKit/vlmeval/vlm/parrot.py:131
↓ 2 callers
Function
process_punctuation
(inText)
VLMEvalKit/vlmeval/smp/misc.py:26
↓ 2 callers
Method
remove_side_quote
(s, syms=[',', '"', "'"])
VLMEvalKit/vlmeval/dataset/mmbench_video.py:140
↓ 2 callers
Function
remove_special_characters
(input_str)
web_demo/web_ability_demo.py:42
↓ 2 callers
Function
repeat_and_pad_image_tokens
( tokenizer: PreTrainedTokenizerBase, prompt: Optional[str], prompt_token_ids: List[int], *,
web_demo/vllm_tools/vllm_file/qwen2.py:99
↓ 2 callers
Function
repeat_and_pad_token
( token: _T, *, repeat_count: int = 1, pad_token_left: Optional[_T] = None,
web_demo/vllm_tools/vllm_file/qwen2.py:110
↓ 2 callers
Function
report_acc_MMT
(df)
VLMEvalKit/vlmeval/dataset/utils/multiple_choice.py:94
↓ 2 callers
Method
reset_dialog
(self)
web_demo/wakeup_and_vad/wakeup_and_vad.py:158
↓ 2 callers
Function
rotate_half
(x)
vita/model/multimodal_encoder/eva_clip/eva_vit.py:45
↓ 2 callers
Method
set_dump_image
(self, dump_image_func)
VLMEvalKit/vlmeval/vlm/base.py:39
↓ 2 callers
Method
set_max_num
(self, dataset)
VLMEvalKit/vlmeval/vlm/internvl_chat.py:260
↓ 2 callers
Method
slow_fast_pooling
(self, temp_img_feats)
vita/model/vita_arch.py:247
↓ 2 callers
Method
split_MMMU
(msgs)
VLMEvalKit/vlmeval/dataset/image_mcq.py:274
↓ 2 callers
Function
subsequent_chunk_mask
Create mask for subsequent steps (size, size) with chunk size, this is for streaming encoder Args: size (int): size of mask
vita/model/vita_tts/masks.py:23
↓ 2 callers
Function
subsequent_chunk_mask
( size: int, ck_size: int, num_l_cks: int = -1, device: torch.device = torch.device("cpu"), )
vita/model/multimodal_encoder/whale/utils.py:88
↓ 2 callers
Function
to_value
Convert the string to Value object. Args: original_string (basestring): Original string corenlp_value (basestring): Optional valu
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:406
↓ 2 callers
Function
to_value_list
Convert a list of strings to a list of Values Args: original_strings (list[basestring]) corenlp_values (list[basestring or None])
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:435
↓ 2 callers
Function
tokenize
Tokenize the text and return the tokens. Parameters: text (str): The text to tokenize. language (str): The language of the text.
VLMEvalKit/vlmeval/dataset/vcr.py:69
↓ 2 callers
Method
transformer_infer
(self, inputs_embeds, cache_position, past_key_values)
vita/model/vita_tts/decoder/decoder.py:294
↓ 2 callers
Function
tsv_unescape_list
Unescape a list in the TSV file. List items are joined with vertical bars (0x5C) Args: x (str or unicode) Returns: a list
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:491
↓ 2 callers
Function
version_cmp
(v1, v2, op='eq')
VLMEvalKit/vlmeval/smp/misc.py:189
↓ 2 callers
Function
zero_template
(crossed_text)
VLMEvalKit/vlmeval/dataset/vcr.py:55
↓ 1 callers
Function
CHECK
(val)
VLMEvalKit/vlmeval/tools.py:258
↓ 1 callers
Function
CIRCULAR
(inp)
VLMEvalKit/vlmeval/tools.py:148
↓ 1 callers
Function
DLIST
(lvl)
VLMEvalKit/vlmeval/tools.py:114
↓ 1 callers
Function
DUDE_acc
(result_file)
VLMEvalKit/vlmeval/dataset/dude.py:13
↓ 1 callers
Function
EVAL
(dataset_name, data_file)
VLMEvalKit/vlmeval/tools.py:346
↓ 1 callers
Function
GPT_context_window
(model)
VLMEvalKit/vlmeval/api/gpt.py:11
↓ 1 callers
Function
HD_transform
(img, im_num=16)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2_4KHD.py:26
↓ 1 callers
Function
Hallusion_rating
(data_file)
VLMEvalKit/vlmeval/dataset/utils/yorn.py:50
↓ 1 callers
Function
LLaVABench_score
(data)
VLMEvalKit/vlmeval/dataset/utils/llavabench.py:55
↓ 1 callers
Function
MATH_V_acc
(result_file)
VLMEvalKit/vlmeval/dataset/utils/mathv.py:143
↓ 1 callers
Function
MLIST
(lvl, size='all')
VLMEvalKit/vlmeval/tools.py:119
↓ 1 callers
Function
MMBenchOfficialServer
(dataset_name)
VLMEvalKit/vlmeval/smp/file.py:77
↓ 1 callers
Function
MME_rating
(data_file)
VLMEvalKit/vlmeval/dataset/utils/yorn.py:4
↓ 1 callers
Function
MMLongBench_acc
(result_file)
VLMEvalKit/vlmeval/dataset/mmlongbench.py:371
↓ 1 callers
Function
MMMU_preproc
(data)
VLMEvalKit/vlmeval/dataset/utils/multiple_choice.py:52
↓ 1 callers
Function
MMMU_result_transfer
(result_path)
VLMEvalKit/vlmeval/utils/result_transfer.py:8
↓ 1 callers
Function
MMTBench_result_transfer
(eval_file, dataset='default', **judge_kwargs)
VLMEvalKit/vlmeval/utils/result_transfer.py:31
↓ 1 callers
Function
MMVet_acc
(result_file)
VLMEvalKit/vlmeval/dataset/utils/mmvet.py:69
↓ 1 callers
Function
MathVista_acc
(result_file)
VLMEvalKit/vlmeval/dataset/utils/mathvista.py:124
↓ 1 callers
Function
POPE_rating
(data_file)
VLMEvalKit/vlmeval/dataset/utils/yorn.py:102
↓ 1 callers
Function
SlideVQA_acc
(result_file)
VLMEvalKit/vlmeval/dataset/slidevqa.py:25
↓ 1 callers
Function
YOrN_match_prompt
(line)
VLMEvalKit/vlmeval/dataset/utils/yorn.py:166
↓ 1 callers
Method
__init__
Construct an Encoder object.
vita/model/vita_tts/encoder/transformer.py:156
↓ 1 callers
Method
__init__
Initialize transducer modules. Args: idim (int): dimension of inputs odim (int): dimension of outputs arg
vita/model/vita_tts/decoder/decoder.py:60
↓ 1 callers
Method
__init__
(self, config_path, ckpt_path, with_encoder=False)
vita/model/vita_tts/decoder/ticodec/vqvae.py:16
↓ 1 callers
Method
__init__
(self, config: Qwen2Config)
vita/model/language_model/vita_fo_qwen2.py:33
↓ 1 callers
Method
__init__
(self, config: MistralConfig)
vita/model/language_model/vita_nemo.py:120
↓ 1 callers
Method
__init__
(self, config: Qwen2Config)
vita/model/language_model/vita_qwen2.py:122
↓ 1 callers
Method
__init__
(self, config: MixtralConfig)
vita/model/language_model/vita_mixtral.py:228
← previous
next →
201–300 of 1,650, ranked by callers