Functions — github.com/PKU-YuanGroup/Chat-UniVi

hub / github.com/PKU-YuanGroup/Chat-UniVi / functions

Functions291 in github.com/PKU-YuanGroup/Chat-UniVi

⨍ Functions 291◇ Types & classes 52

Functionannotate

Evaluates question and answer pairs using GPT-3 and returns a score for temporal understanding.

ChatUniVi/eval/evaluate/evaluate_benchmark_4_temporal.py:29

Functionannotate

Evaluates question and answer pairs using GPT-3 Returns a score for correctness.

ChatUniVi/eval/evaluate/evaluate_benchmark_1_correctness.py:29

Functionannotate

Evaluates question and answer pairs using GPT-3 and returns a score for detailed orientation.

ChatUniVi/eval/evaluate/evaluate_benchmark_2_detailed_orientation.py:29

Functionannotate

Evaluates question and answer pairs using GPT-3 Returns a score for correctness.

ChatUniVi/eval/evaluate/evaluate_video_qa.py:29

Functionannotate

Evaluates question and answer pairs using GPT-3 and returns a score for contextual understanding.

ChatUniVi/eval/evaluate/evaluate_benchmark_3_context.py:29

Functionannotate

Evaluates question and answer pairs using GPT-3 and returns a score for consistency.

ChatUniVi/eval/evaluate/evaluate_benchmark_5_consistency.py:29

Functionbuild_logger

(logger_name, logger_filename)

ChatUniVi/utils.py:17

Functionclear_history

(state, state_)

main_demo_7B.py:108

Functionclear_history

ChatUniVi/model/multimodal_projector/builder.py:14

Methodconfig

(self)

ChatUniVi/model/multimodal_encoder/eva_encoder.py:69

Methodconfig

(self)

ChatUniVi/model/multimodal_encoder/clip_encoder.py:71

Functionconvert_caps

(results)

ChatUniVi/eval/evaluate/evaluate_science_qa.py:20

Methoddevice

(self)

ChatUniVi/model/multimodal_encoder/eva_encoder.py:65

Methoddevice

(self)

ChatUniVi/model/multimodal_encoder/clip_encoder.py:67

Methoddict

(self)

ChatUniVi/conversation.py:202

Methoddtype

(self)

ChatUniVi/model/multimodal_encoder/eva_encoder.py:61

Methoddtype

(self)

ChatUniVi/model/multimodal_encoder/clip_encoder.py:63

Methoddummy_feature

(self)

ChatUniVi/model/multimodal_encoder/eva_encoder.py:57

Methoddummy_feature

(self)

ChatUniVi/model/multimodal_encoder/clip_encoder.py:59

Methodexpand2square

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

ChatUniVi/conversation.py:119

Methodexpand2square

(pil_img, background_color)

ChatUniVi/train/train.py:825

Methodextra_repr

(self)

ChatUniVi/model/multimodal_encoder/eva_vit.py:42

Functionforward

Input shape: Batch x Time x Channel attention_mask: [bsz, q_len]

ChatUniVi/train/llama_flash_attn_monkey_patch.py:19

Methodforward

(self, x)

ChatUniVi/model/cluster.py:87

Methodforward

(self, token_dict, sample_ratio=None)

ChatUniVi/model/cluster.py:233

Methodforward

(self, inputs)

ChatUniVi/model/cluster.py:280

Methodforward

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

ChatUniVi/model/language_model/llama.py:36

Methodforward

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

ChatUniVi/model/language_model/phi.py:59

Methodforward

(self, input_ids: torch.LongTensor)

ChatUniVi/model/language_model/language_model/modeling_phi.py:78

Methodforward

( self, qkv: torch.Tensor, kv: Optional[torch.Tensor] = None, seqlen_offset: i

ChatUniVi/model/language_model/language_model/modeling_phi.py:259

Methodforward

(self, hidden_states: torch.FloatTensor)

ChatUniVi/model/language_model/language_model/modeling_phi.py:321

Methodforward

( self, qkv: torch.FloatTensor, causal: bool = None, key_padding_mask: Optiona

ChatUniVi/model/language_model/language_model/modeling_phi.py:351

Methodforward

( self, q: torch.FloatTensor, kv: torch.FloatTensor, causal: bool = None,

ChatUniVi/model/language_model/language_model/modeling_phi.py:411

Methodforward

( self, x: torch.FloatTensor, past_key_values: Optional[InferenceParams] = None,

ChatUniVi/model/language_model/language_model/modeling_phi.py:711

Methodforward

( self, hidden_states: torch.FloatTensor, past_key_values: Optional[Union[torch.FloatT

ChatUniVi/model/language_model/language_model/modeling_phi.py:765

Methodforward

(self, hidden_states: torch.FloatTensor)

ChatUniVi/model/language_model/language_model/modeling_phi.py:806

Methodforward

(self, logits: torch.FloatTensor, labels: torch.LongTensor)

ChatUniVi/model/language_model/language_model/modeling_phi.py:828

Methodforward

( self, input_ids: torch.LongTensor, past_key_values: Optional[Union[torch.FloatTensor

ChatUniVi/model/language_model/language_model/modeling_phi.py:912

Methodforward

( self, input_ids: torch.LongTensor, past_key_values: Optional[Union[torch.FloatTensor

ChatUniVi/model/language_model/language_model/modeling_phi.py:969

Methodforward

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

ChatUniVi/model/multimodal_projector/builder.py:10

Methodforward

(self, x)

ChatUniVi/model/multimodal_projector/builder.py:28

Methodforward

(self, x)

ChatUniVi/model/multimodal_encoder/eva_vit.py:39

Methodforward

(self, x)

ChatUniVi/model/multimodal_encoder/eva_vit.py:56

Methodforward

(self, x, rel_pos_bias=None)

ChatUniVi/model/multimodal_encoder/eva_vit.py:120

Methodforward

(self, x, rel_pos_bias=None)

ChatUniVi/model/multimodal_encoder/eva_vit.py:175

Methodforward

(self, x, **kwargs)

ChatUniVi/model/multimodal_encoder/eva_vit.py:201

Methodforward

(self)

ChatUniVi/model/multimodal_encoder/eva_vit.py:241

Methodforward

(self, x)

ChatUniVi/model/multimodal_encoder/eva_vit.py:355

Methodforward

(self, images, select_feature='patch')

ChatUniVi/model/multimodal_encoder/eva_encoder.py:43

Methodforward

(self, images, select_feature='patch')

ChatUniVi/model/multimodal_encoder/clip_encoder.py:45

Functiongenerate

(image1, image2, video, textbox_in, first_run, state, state_, images_tensor)

main_demo_7B.py:31

Functiongenerate

(image1, image2, video, textbox_in, first_run, state, state_, images_tensor)

main_demo_13B.py:31

Functionget_chunk

(lst, n, k)

ChatUniVi/eval/model_video_consistency.py:24

Functionget_chunk

(lst, n, k)

ChatUniVi/eval/model_video_general.py:24

Functionget_chunk

(lst, n, k)

ChatUniVi/eval/model_video_qa.py:29

Methodget_classifier

(self)

ChatUniVi/model/multimodal_encoder/eva_vit.py:322

Methodget_decoder

(self)

ChatUniVi/model/language_model/language_model/modeling_phi.py:957

Methodget_input_embeddings

(self)

ChatUniVi/model/language_model/language_model/modeling_phi.py:960

Methodget_model

(self)

ChatUniVi/model/language_model/llama.py:33

Methodget_model

(self)

ChatUniVi/model/language_model/phi.py:53

Functionget_model_name_from_path

(model_path)

ChatUniVi/mm_utils.py:41

Methodget_w

(weights, keyword)

ChatUniVi/model/arch.py:67

Functionget_world_size

()

ChatUniVi/model/multimodal_encoder/utils.py:41

Methodhidden_size

(self)

ChatUniVi/model/multimodal_encoder/eva_encoder.py:76

Methodhidden_size

(self)

ChatUniVi/model/multimodal_encoder/clip_encoder.py:78

Functioninit_distributed_mode

(args)

ChatUniVi/model/multimodal_encoder/utils.py:57

Functionload_image_from_base64

(image)

ChatUniVi/mm_utils.py:10

Functionmain_process

(func)

ChatUniVi/model/multimodal_encoder/utils.py:107

Functionmake_inputs_require_grad

(module, input, output)

ChatUniVi/train/train.py:1053

Methodnum_patches

(self)

ChatUniVi/model/multimodal_encoder/eva_encoder.py:80

Methodnum_patches

(self)

ChatUniVi/model/multimodal_encoder/clip_encoder.py:82

Methodpositional_encoding

(self, x, num_features=1024, max_len=64)

ChatUniVi/model/arch.py:101

Methodprepare_inputs_for_generation

( self, input_ids, past_key_values=None, attention_mask=None, inputs_embeds=None, **kwargs )

ChatUniVi/model/language_model/llama.py:98

Methodprepare_inputs_for_generation

( self, input_ids, past_key_values=None, attention_mask=None, inputs_embeds=None, **kwargs )

ChatUniVi/model/language_model/phi.py:118

Methodprepare_inputs_for_generation

( self, input_ids: torch.LongTensor, past_key_values: Optional[Union[torch.FloatTensor

ChatUniVi/model/language_model/language_model/modeling_phi.py:863

Methodpreprocess

(self, item, return_tensors)

ChatUniVi/model/multimodal_encoder/processor.py:30

Methodpreprocess

(self, item, return_tensors)

ChatUniVi/model/multimodal_encoder/processor.py:67

Functionpretty_print_semaphore

(semaphore)

ChatUniVi/utils.py:123

Functionprocess_images

(images, image_processor, model_cfg)

ChatUniVi/mm_utils.py:14

ChatUniVi/model/multimodal_encoder/eva_vit.py:306

Methodreset_classifier

(self, num_classes, global_pool='')

ChatUniVi/model/multimodal_encoder/eva_vit.py:325

Methodset_decoder

(self, decoder)

ChatUniVi/model/language_model/language_model/modeling_phi.py:953

Methodset_input_embeddings

(self, new_embeddings: nn.Embedding)

ChatUniVi/model/language_model/language_model/modeling_phi.py:909

Methodset_input_embeddings

(self, value)

ChatUniVi/model/language_model/language_model/modeling_phi.py:949

Methodset_output_embeddings

(self, new_embeddings: nn.Linear)

ChatUniVi/model/language_model/language_model/modeling_phi.py:966

Functionsplit

(image, patch_size=14, idx=None)

visualization.py:10

Functionviolates_moderation

Check whether the text violates OpenAI moderation API.

ChatUniVi/utils.py:102

Functionwrapper

(*args, **kwargs)

ChatUniVi/model/multimodal_encoder/utils.py:109

← previous201–291 of 291, ranked by callers