Functions — github.com/VITA-MLLM/VITA

CodeHub MCPcopy Create free account

hub / github.com/VITA-MLLM/VITA / functions

Functions1,650 in github.com/VITA-MLLM/VITA

⨍ Functions 1,650◇ Types & classes 320↳ Endpoints 1

Method__getitem__

vita/util/data_utils_video_audio_neg_patch_fo.py:880

Method__getitem__

vita/util/data_utils_video_patch_audio.py:786

Method__getitem__

vita/util/data_utils_video_audio_neg_frameCat.py:614

Method__getitem__

vita/util/data_utils_video_audio.py:421

Method__getitem__

vita/util/data_utils_video_audio_patch_sf.py:740

Method__getitem__

VLMEvalKit/vlmeval/dataset/video_base.py:38

Method__getitem__

VLMEvalKit/vlmeval/dataset/image_base.py:74

Method__getitem__

VLMEvalKit/vlmeval/dataset/text_base.py:26

VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:270

VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:304

VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:366

vita/model/vita_arch.py:14

( self, enc_out_dim: int = 512, llm_embed_dim: int = 4096, )

vita/model/vita_tts/adapter.py:60

( self, enc_out_dim: int = 512, llm_embed_dim: int = 4096, kernel_size: int =

vita/model/vita_tts/adapter.py:73

vita/model/vita_tts/pipeline.py:9

( self, encoder: torch.nn.Module, llm_path: str, freeze_llm: bool = True,

vita/model/vita_tts/audioLLM.py:21

vita/model/vita_tts/encoder/subsampling.py:6

Construct an Conv2dSubsampling4 object.

vita/model/vita_tts/encoder/subsampling.py:24

Args: mean (torch.Tensor): mean stats istd (torch.Tensor): inverse std, std which is 1.0 / std

vita/model/vita_tts/encoder/cmvn.py:8

Construct an PositionalEncoding object.

vita/model/vita_tts/encoder/attention.py:15

Initialize class.

vita/model/vita_tts/encoder/attention.py:78

Construct an PositionwiseFeedForward object.

vita/model/vita_tts/encoder/attention.py:130

Initialize MultiLayeredConv1d module. Args: in_chans (int): Number of input channels. hidden_chans (int): Number of h

vita/model/vita_tts/encoder/attention.py:158

Construct an MultiHeadedAttention object.

vita/model/vita_tts/encoder/attention.py:276

Construct an TransformerLayer object.

vita/model/vita_tts/encoder/transformer.py:57

( self, input_dim, overview_conf = None, para_conf = None,

vita/model/vita_tts/encoder/encoder.py:46

(self, ignore_index=-1)

vita/model/vita_tts/decoder/decoder.py:17

(self, model_path)

vita/model/vita_tts/decoder/llm2tts.py:18

(self, in_channels, hidden_channels, out_channels, kernel_size=3, stride=1)

vita/model/vita_tts/decoder/ticodec/models.py:23

(self, h, channels, kernel_size=3, dilation=(1, 3, 5))

vita/model/vita_tts/decoder/ticodec/models.py:60

(self, h, channels, kernel_size=3, dilation=(1, 3))

vita/model/vita_tts/decoder/ticodec/models.py:134

Initializes the Generator module. Parameters: - h (object): Configuration object containing hyperparameters for the generato

vita/model/vita_tts/decoder/ticodec/models.py:170

(self, period, kernel_size=5, stride=3, use_spectral_norm=False)

vita/model/vita_tts/decoder/ticodec/models.py:258

vita/model/vita_tts/decoder/ticodec/models.py:311

(self, use_spectral_norm=False)

vita/model/vita_tts/decoder/ticodec/models.py:338

vita/model/vita_tts/decoder/ticodec/models.py:366

(self, n_e, e_dim)

vita/model/vita_tts/decoder/ticodec/models.py:526

vita/model/vita_tts/decoder/ticodec/models.py:541

(self, config_path, model_path, sample_rate=24000)

vita/model/vita_tts/decoder/ticodec/vqvae_tester.py:10

(self, *args, **kwargs)

vita/model/vita_tts/decoder/ticodec/vqvae.py:11

vita/model/language_model/vita_fo_qwen2.py:40

vita/model/language_model/vita_nemo.py:127

vita/model/language_model/vita_qwen2.py:129

vita/model/language_model/vita_mixtral.py:235

vita/model/multimodal_projector/builder.py:13

(self, config=None)

vita/model/multimodal_projector/builder.py:25

(self, config=None)

vita/model/multimodal_projector/builder.py:48

(self, config=None)

vita/model/multimodal_projector/builder.py:78

(self, config=None)

vita/model/multimodal_projector/builder.py:106

(self, vision_tower, args, delay_load=False)

vita/model/multimodal_encoder/clip/clip_encoder.py:7

(self, vision_tower, args, delay_load=False)

vita/model/multimodal_encoder/siglip/siglip_encoder.py:83

( self, dataset_conf: dict = None, )

vita/model/multimodal_encoder/whale/init_model.py:29

( self, encoder: torch.nn.Module, llm_path: str, freeze_llm: bool = True,

vita/model/multimodal_encoder/whale/init_model.py:64

( self, enc_out_dim: int = 512, llm_embed_dim: int = 4096, )

vita/model/multimodal_encoder/whale/adapter.py:55

( self, enc_out_dim: int = 512, llm_embed_dim: int = 4096, kernel_size: int =

vita/model/multimodal_encoder/whale/adapter.py:69

Args: mean (torch.Tensor): mean stats istd (torch.Tensor): inverse std, std which is 1.0 / std

vita/model/multimodal_encoder/whale/cmvn.py:8

vita/model/multimodal_encoder/whale/module/component/subsampling.py:6

Construct an Conv2dSubsampling4 object.

vita/model/multimodal_encoder/whale/module/component/subsampling.py:25

(self, in_channels, n_layer=1, d_state=16, d_conv=4, expand=4, bidirectional=False)

vita/model/multimodal_encoder/whale/module/component/mamba.py:23

Construct an TransformerLayer object.

vita/model/multimodal_encoder/whale/module/component/transformer.py:81

(self, input_dim, overview_conf=None, para_conf=None, global_cmvn=None)

vita/model/multimodal_encoder/whale/module/encoder/encoder.py:56

( self, input_dim, output_dim, kernel_size, stride, causal_con

vita/model/multimodal_encoder/whale/module/layer/conv1d.py:7

( self, input_dim, output_dim, kernel_size, stride, causal_conv, dilation, dropout_rate )

vita/model/multimodal_encoder/whale/module/layer/dtcblock.py:11

Construct an PositionalEncoding object.

vita/model/multimodal_encoder/whale/module/layer/attention.py:18

Initialize class.

vita/model/multimodal_encoder/whale/module/layer/attention.py:79

Construct an PositionwiseFeedForward object.

vita/model/multimodal_encoder/whale/module/layer/attention.py:138

Initialize MultiLayeredConv1d module. Args: in_chans (int): Number of input channels. hidden_chans (int): Number of h

vita/model/multimodal_encoder/whale/module/layer/attention.py:168

Construct an MultiHeadedAttention object.

vita/model/multimodal_encoder/whale/module/layer/attention.py:282

(self, in_dim, hidden_dim)

vita/model/multimodal_encoder/whale/module/layer/attention.py:534

( self, input_dim, out_dim, hidden_dim, left_frame=1, right_fr

vita/model/multimodal_encoder/whale/module/layer/fsmn.py:7

( self, num_channels=3, patch_size=14, image_size=224, qkv_bias=False,

vita/model/multimodal_encoder/internvit/configuration_intern_vit.py:63

(self, vision_tower, args, delay_load=False)

vita/model/multimodal_encoder/internvit/internvit_encoder.py:9

(self, hidden_size, eps=1e-6)

vita/model/multimodal_encoder/internvit/modeling_intern_vit.py:35

(self, config: InternVisionConfig)

vita/model/multimodal_encoder/internvit/modeling_intern_vit.py:69

(self, config: InternVisionConfig)

vita/model/multimodal_encoder/internvit/modeling_intern_vit.py:128

(self, config: InternVisionConfig, drop_path_rate: float)

vita/model/multimodal_encoder/internvit/modeling_intern_vit.py:221

(self, config: InternVisionConfig)

vita/model/multimodal_encoder/internvit/modeling_intern_vit.py:266

(self, config: InternVisionConfig)

vita/model/multimodal_encoder/internvit/modeling_intern_vit.py:326

(self, softmax_scale=None, attention_dropout=0.0, device=None, dtype=None)

vita/model/multimodal_encoder/internvit/flash_attention.py:27

(self, vision_tower, args, delay_load=False)

vita/model/multimodal_encoder/eva_clip/eva_clip_encoder.py:9

(self, mean=None, std=None)

vita/model/multimodal_encoder/eva_clip/eva_clip_processors.py:23

(self, image_size=224, mean=None, std=None, min_scale=0.5, max_scale=1.0)

vita/model/multimodal_encoder/eva_clip/eva_clip_processors.py:35

( self, dim, pt_seq_len, ft_seq_len=None, custom_freqs=None, f

vita/model/multimodal_encoder/eva_clip/eva_vit.py:53

(self, prob, exclude_first_token=True)

vita/model/multimodal_encoder/eva_clip/eva_vit.py:128

(self, drop_prob=None)

vita/model/multimodal_encoder/eva_clip/eva_vit.py:184

( self, in_features, hidden_features=None, out_features=None, act_laye

vita/model/multimodal_encoder/eva_clip/eva_vit.py:230

( self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_

vita/model/multimodal_encoder/eva_clip/eva_vit.py:264

( self, dim, num_heads, mlp_ratio=4.0, qkv_bias=False, qk_scal

vita/model/multimodal_encoder/eva_clip/eva_vit.py:431

(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768)

vita/model/multimodal_encoder/eva_clip/eva_vit.py:528

(self, window_size, num_heads)

vita/model/multimodal_encoder/eva_clip/eva_vit.py:551

( self, img_size=224, patch_size=16, in_chans=3, num_classes=1000,

vita/model/multimodal_encoder/eva_clip/eva_vit.py:594

(self, vision_tower_path)

vita/model/multimodal_encoder/eva_clip/eva_vit.py:946

( self, batch_size: int, world_size: int, lengths: Optional[List[int]] = None,

vita/train/vita_trainer.py:123

(self, tokenizer: transformers.PreTrainedTokenizer, data_args: DataArguments)

vita/util/data_utils_video_audio_patch.py:688

(self, tokenizer: transformers.PreTrainedTokenizer, data_args: DataArguments)

vita/util/data_utils_video_audio_neg_patch.py:830

(self, tokenizer: transformers.PreTrainedTokenizer, data_args: DataArguments)

vita/util/data_utils_video_audio_neg_patch_fo.py:828

(self, logger, log_level=logging.INFO)

vita/util/utils.py:73

(self, tokenizer: transformers.PreTrainedTokenizer, data_args: DataArguments)

vita/util/data_utils_video_patch_audio.py:734

(self, tokenizer: transformers.PreTrainedTokenizer, data_args: DataArguments)

vita/util/data_utils_video_audio_neg_frameCat.py:562

(self, tokenizer: transformers.PreTrainedTokenizer, data_args: DataArguments)

vita/util/data_utils_video_audio.py:374

← previous next →801–900 of 1,650, ranked by callers