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

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/videomme.py:213

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/video_base.py:75

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/image_base.py:164

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/image_mcq.py:182

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/image_mcq.py:417

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/image_mcq.py:588

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/image_vqa.py:43

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/image_vqa.py:104

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/image_vqa.py:170

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/image_vqa.py:231

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/image_vqa.py:289

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/image_vqa.py:330

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/image_vqa.py:383

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/image_vqa.py:430

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/image_vqa.py:488

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/image_mt.py:88

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/mvbench.py:335

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/mvbench.py:535

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/text_base.py:87

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/slidevqa.py:142

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/__init__.py:85

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/vcr.py:263

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/image_yorn.py:24

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/mmbench_video.py:204

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/mmlongbench.py:535

(self, eval_file, **kwargs)

VLMEvalKit/vlmeval/dataset/image_caption.py:62

(self, eval_file, **judge_kwargs)

VLMEvalKit/vlmeval/dataset/text_mcq.py:42

Methodexpand2square

(pil_img, background_color=(122, 116, 104))

vita/conversation.py:189

Methodexpand2square

(pil_img, background_color)

vita/util/data_utils_video_audio_patch.py:769

Methodexpand2square

(pil_img, background_color)

vita/util/data_utils_video_audio_neg_patch.py:911

Methodexpand2square

(pil_img, background_color)

vita/util/data_utils_video_audio_neg_patch_fo.py:909

Methodexpand2square

(pil_img, background_color)

vita/util/data_utils_video_patch_audio.py:815

Methodexpand2square

(pil_img, background_color)

vita/util/data_utils_video_audio_neg_frameCat.py:643

Methodexpand2square

(pil_img, background_color)

vita/util/data_utils_video_audio.py:444

Methodexpand2square

(pil_img, background_color)

vita/util/data_utils_video_audio_patch_sf.py:769

Methodextra_repr

vita/model/multimodal_encoder/eva_clip/eva_vit.py:191

Functionextract_characters_regex

videomme/parse_answer.py:52

Functionextract_characters_regex

(s, choices=['(A)', '(B)', '(C)', '(D)', '(E)'])

VLMEvalKit/vlmeval/dataset/utils/multiple_choice.py:446

Functionfeature_loss

(fmap_r, fmap_g)

vita/model/vita_tts/decoder/ticodec/models.py:395

Functionforward

( model, input, scales=None, img_sizes=None, max_split_size=None, resize_output_to_idx

vita/util/s2wrapper/core.py:17

x: B, T, enc_out_dim mask: (B, T) or (B, 1, T)

vita/model/vita_tts/adapter.py:33

(self, x, mask_pad)

vita/model/vita_tts/adapter.py:69

x: B, T, enc_out_dim mask: (B, T) or (B, 1, T)

vita/model/vita_tts/adapter.py:112

Subsample x. Args: x (torch.Tensor): Input tensor (#batch, time, idim). x_mask (torch.Tensor): Input mask (#batch, 1,

vita/model/vita_tts/encoder/subsampling.py:41

(self, xs, ilens, masks)

vita/model/vita_tts/encoder/subsampling.py:98

Args: x (torch.Tensor): (batch, max_len, feat_dim) Returns: (torch.Tensor): normalized feature

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

Add positional encoding. Args: x (torch.Tensor): Input. Its shape is (batch, time, ...) offset (int): position offset

vita/model/vita_tts/encoder/attention.py:37

Compute positional encoding. Args: x (torch.Tensor): Input tensor (batch, time, `*`). Returns: torch.Tensor: E

vita/model/vita_tts/encoder/attention.py:90

Forward funciton.

vita/model/vita_tts/encoder/attention.py:137

Calculate forward propagation. Args: x (Tensor): Batch of input tensors (B, ..., in_chans). Returns: Tensor:

vita/model/vita_tts/encoder/attention.py:185

Calculate forward propagation. Args: x (Tensor): Batch of input tensors (B, ..., in_chans). Returns: Tensor:

vita/model/vita_tts/encoder/attention.py:241

Compute 'Scaled Dot Product Attention'. :param torch.Tensor query: (batch, time1, size) :param torch.Tensor key: (batch, time2, size)

vita/model/vita_tts/encoder/attention.py:350

vita/model/vita_tts/encoder/transformer.py:29

Compute encoded features. :param torch.Tensor x: encoded source features (batch, max_time_in, size) :param torch.Tensor mask: mask fo

vita/model/vita_tts/encoder/transformer.py:75

Embed positions in tensor. :param torch.Tensor xs: input tensor :param torch.Tensor masks: input mask :return: position embed

vita/model/vita_tts/encoder/transformer.py:237

Forward pass through the encoder. Parameters: - xs: torch.Tensor, shape (batch_size, sequence_length, input_dim)

vita/model/vita_tts/encoder/encoder.py:104

logits: B*T1*D target: B*T2

vita/model/vita_tts/decoder/decoder.py:21

vita/model/vita_tts/decoder/decoder.py:190

x --- [B, in_channels, T] out -- [B, out_channels]

vita/model/vita_tts/decoder/ticodec/models.py:45

vita/model/vita_tts/decoder/ticodec/models.py:117

vita/model/vita_tts/decoder/ticodec/models.py:157

Forward pass of the Generator module. Parameters: - x (torch.Tensor): Input tensor of shape [B, C, T], where B is the batch

vita/model/vita_tts/decoder/ticodec/models.py:211

vita/model/vita_tts/decoder/ticodec/models.py:288

(self, y, y_hat)

vita/model/vita_tts/decoder/ticodec/models.py:321

vita/model/vita_tts/decoder/ticodec/models.py:352

(self, y, y_hat)

vita/model/vita_tts/decoder/ticodec/models.py:376

(self, x, xx=None)

vita/model/vita_tts/decoder/ticodec/models.py:475

vita/model/vita_tts/decoder/ticodec/models.py:531

(self, xin, global_style)

vita/model/vita_tts/decoder/ticodec/models.py:639

(self, wav_path)

vita/model/vita_tts/decoder/ticodec/vqvae_tester.py:16

(self, x, global_style_token)

vita/model/vita_tts/decoder/ticodec/vqvae.py:37

( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = N

vita/model/language_model/vita_fo_qwen2.py:56

( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = N

vita/model/language_model/vita_nemo.py:139

( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = N

vita/model/language_model/vita_qwen2.py:141

( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = N

vita/model/language_model/vita_mixtral.py:249

(self, x, *args, **kwargs)

vita/model/multimodal_projector/builder.py:16

vita/model/multimodal_projector/builder.py:31

vita/model/multimodal_projector/builder.py:54

vita/model/multimodal_projector/builder.py:95

vita/model/multimodal_projector/builder.py:110

vita/model/multimodal_projector/builder.py:129

vita/model/multimodal_encoder/clip/clip_encoder.py:35

vita/model/multimodal_encoder/siglip/siglip_encoder.py:36

vita/model/multimodal_encoder/siglip/siglip_encoder.py:126

( self, speech: torch.Tensor, speech_lengths: torch.Tensor, )

vita/model/multimodal_encoder/whale/init_model.py:122

x: B, T, enc_out_dim mask: (B, T) or (B, 1, T)

vita/model/multimodal_encoder/whale/adapter.py:27

(self, x, mask_pad)

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

x: B, T, enc_out_dim mask: (B, T) or (B, 1, T)

vita/model/multimodal_encoder/whale/adapter.py:108

Args: x (torch.Tensor): (batch, max_len, feat_dim) Returns: (torch.Tensor): normalized feature

vita/model/multimodal_encoder/whale/cmvn.py:21

(self, x: torch.Tensor, x_mask: torch.Tensor)

vita/model/multimodal_encoder/whale/module/component/subsampling.py:38

(self, xs, ilens, masks)

vita/model/multimodal_encoder/whale/module/component/subsampling.py:71

vita/model/multimodal_encoder/whale/module/component/mamba.py:59

Embed positions in tensor. :param torch.Tensor xs: input tensor :param torch.Tensor masks: input mask :return: position embed

vita/model/multimodal_encoder/whale/module/component/mamba.py:120

vita/model/multimodal_encoder/whale/module/component/transformer.py:38

Compute encoded features. :param torch.Tensor x: encoded source features (batch, max_time_in, size) :param torch.Tensor mask: mask fo

vita/model/multimodal_encoder/whale/module/component/transformer.py:100

Embed positions in tensor. :param torch.Tensor xs: input tensor :param torch.Tensor masks: input mask :return: position embed

vita/model/multimodal_encoder/whale/module/component/transformer.py:374

Encoder forward :param torch.Tensor xs_pad: batch of padded input sequences (B, Tmax, D) :param torch.Tensor ilens: batch of lengths

vita/model/multimodal_encoder/whale/module/encoder/encoder.py:121

vita/model/multimodal_encoder/whale/module/layer/conv1d.py:49

vita/model/multimodal_encoder/whale/module/layer/dtcblock.py:50

Add positional encoding. Args: x (torch.Tensor): Input. Its shape is (batch, time, ...) offset (int): position offset

vita/model/multimodal_encoder/whale/module/layer/attention.py:38

← previous next →1,201–1,300 of 1,650, ranked by callers