MCPcopy Create free account

hub / github.com/PKU-YuanGroup/Video-LLaVA / functions

Functions670 in github.com/PKU-YuanGroup/Video-LLaVA

⨍ Functions 670◇ Types & classes 125↳ Endpoints 14
↓ 1 callersFunctionget_chunk
(lst, n, k)
videollava/eval/model_vqa_science.py:24
↓ 1 callersFunctionget_chunk
(lst, n, k)
videollava/eval/model_vqa.py:24
↓ 1 callersFunctionget_chunk
(lst, n, k)
videollava/eval/video/run_inference_video_qa_act.py:23
↓ 1 callersFunctionget_chunk
(lst, n, k)
videollava/eval/video/run_inference_video_qa.py:23
↓ 1 callersFunctionget_depth_transform
(config)
videollava/model/multimodal_encoder/languagebind/depth/processing_depth.py:44
↓ 1 callersFunctionget_eval
(content: str, max_tokens: int)
videollava/eval/eval_gpt_review_bench.py:11
↓ 1 callersFunctionget_eval
(content: str, max_tokens: int)
videollava/eval/eval_gpt_review_visual.py:11
↓ 1 callersMethodget_image_tower
(self)
videollava/model/llava_arch.py:131
↓ 1 callersFunctionget_image_transform
(config)
videollava/model/multimodal_encoder/languagebind/image/processing_image.py:15
↓ 1 callersMethodget_images
(self, return_pil=False)
videollava/conversation.py:109
↓ 1 callersFunctionget_mm_adapter_state_maybe_zero_3
(named_params, keys_to_match)
videollava/train/train.py:170
↓ 1 callersFunctionget_mm_adapter_state_maybe_zero_3
(named_params, keys_to_match)
videollava/train/llava_trainer.py:32
↓ 1 callersFunctionget_modality_length_grouped_indices
(lengths, batch_size, world_size, generator=None)
videollava/train/llava_trainer.py:60
↓ 1 callersFunctionget_model_output
(model, video_processor, tokenizer, video, qs, args)
videollava/eval/video/run_inference_video_qa_act.py:49
↓ 1 callersFunctionget_options
(row, options)
videollava/eval/model_vqa_mmbench.py:44
↓ 1 callersFunctionget_peft_state_maybe_zero_3
(named_params, bias)
videollava/train/train.py:137
↓ 1 callersFunctionget_peft_state_non_lora_maybe_zero_3
(named_params, require_grad_only=True)
videollava/train/train.py:162
↓ 1 callersMethodget_prompt
(self)
videollava/conversation.py:29
↓ 1 callersFunctionget_thermal_transform
(config)
videollava/model/multimodal_encoder/languagebind/thermal/processing_thermal.py:15
↓ 1 callersFunctionget_tokenize_len
(prompts)
videollava/train/train.py:639
↓ 1 callersMethodget_video_tower
(self)
videollava/model/llava_arch.py:134
↓ 1 callersFunctionget_video_transform
(config)
videollava/model/multimodal_encoder/languagebind/video/processing_video.py:26
↓ 1 callersFunctionimage_parser
(args)
videollava/eval/run_llava.py:29
↓ 1 callersFunctioninit_on_device
Device initialization context manager. A context manager under which models are initialized with all parameters on the specified device.
videollava/model/language_model/mpt/meta_init_context.py:37
↓ 1 callersMethodinitialize_vision_modules
(self, model_args, fsdp=None)
videollava/model/llava_arch.py:51
↓ 1 callersMethodinitialize_vision_tokenizer
(self, model_args, tokenizer)
videollava/model/llava_arch.py:348
↓ 1 callersFunctioninsert_separator
(X, sep)
videollava/mm_utils.py:46
↓ 1 callersFunctionintersectionRate
(c1, c2)
videollava/eval/eval_gqa.py:307
↓ 1 callersFunctionintersectionSize
(c1, c2)
videollava/eval/eval_gqa.py:303
↓ 1 callersMethodlist_models
(self)
videollava/serve/controller.py:112
↓ 1 callersFunctionload
(ckpt_dir, model_type, cache_dir)
videollava/eval/eval_mmlu.py:134
↓ 1 callersFunctionload_from_hf
(repo_id, filename, subfolder=None)
videollava/model/builder.py:66
↓ 1 callersFunctionload_image
(image_file)
videollava/eval/model_vqa_qbench.py:19
↓ 1 callersFunctionload_image
(image_file)
videollava/eval/run_llava.py:34
↓ 1 callersFunctionload_images
(image_files)
videollava/eval/run_llava.py:43
↓ 1 callersMethodload_model
(self)
videollava/model/multimodal_encoder/languagebind/__init__.py:112
↓ 1 callersMethodload_model
(self)
videollava/model/multimodal_encoder/languagebind/__init__.py:194
↓ 1 callersFunctionmain
(args)
videollava/serve/cli.py:25
↓ 1 callersFunctionmain
()
videollava/serve/test_message.py:9
↓ 1 callersFunctionmain
(ckpt_dir: str, param_size: str, model_type: str, cache_dir: str)
videollava/eval/eval_mmlu.py:196
↓ 1 callersFunctionmain
Main function to control the flow of the program.
videollava/eval/video/eval_benchmark_3_context.py:80
↓ 1 callersFunctionmain
Main function to control the flow of the program.
videollava/eval/video/eval_benchmark_4_temporal.py:79
↓ 1 callersFunctionmain
Main function to control the flow of the program.
videollava/eval/video/eval_video_qa.py:79
↓ 1 callersFunctionmain
Main function to control the flow of the program.
videollava/eval/video/eval_benchmark_5_consistency.py:85
↓ 1 callersFunctionmain
Main function to control the flow of the program.
videollava/eval/video/eval_benchmark_2_detailed_orientation.py:80
↓ 1 callersFunctionmain
Main function to control the flow of the program.
videollava/eval/video/eval_benchmark_1_correctness.py:80
↓ 1 callersFunctionmake_delta
(base_model_path, target_model_path, delta_path, hub_repo_id)
videollava/model/make_delta.py:13
↓ 1 callersFunctionmake_list_of_images
(x)
videollava/model/multimodal_encoder/languagebind/image/processing_image.py:10
↓ 1 callersFunctionmake_list_of_images
(x)
videollava/model/multimodal_encoder/languagebind/audio/processing_audio.py:11
↓ 1 callersFunctionmake_list_of_images
(x)
videollava/model/multimodal_encoder/languagebind/depth/processing_depth.py:12
↓ 1 callersFunctionmake_list_of_images
(x)
videollava/model/multimodal_encoder/languagebind/thermal/processing_thermal.py:10
↓ 1 callersFunctionmake_list_of_images
(x)
videollava/model/multimodal_encoder/languagebind/video/processing_video.py:21
↓ 1 callersFunctionmake_supervised_data_module
Make dataset and collator for supervised fine-tuning.
videollava/train/train.py:869
↓ 1 callersFunctionmaybe_zero_3
(param, ignore_status=False, name=None)
videollava/train/llava_trainer.py:18
↓ 1 callersFunctionmerge_lora
(args)
scripts/merge_lora_weights.py:6
↓ 1 callersFunctionopencv_loader
(path)
videollava/model/multimodal_encoder/languagebind/depth/processing_depth.py:17
↓ 1 callersFunctionparse_args
()
scripts/convert_vizwiz_for_submission.py:8
↓ 1 callersFunctionparse_args
()
scripts/convert_vqav2_for_submission.py:8
↓ 1 callersFunctionparse_args
()
videollava/eval/summarize_gpt_review.py:9
↓ 1 callersFunctionparse_args
Parse command-line arguments.
videollava/eval/video/run_inference_video_qa_act.py:27
↓ 1 callersFunctionparse_args
Parse command-line arguments.
videollava/eval/video/run_inference_benchmark_consistency.py:13
↓ 1 callersFunctionparse_args
()
videollava/eval/video/eval_benchmark_3_context.py:9
↓ 1 callersFunctionparse_args
Parse command-line arguments.
videollava/eval/video/run_inference_video_qa.py:27
↓ 1 callersFunctionparse_args
Parse command-line arguments.
videollava/eval/video/run_inference_benchmark_general.py:13
↓ 1 callersFunctionparse_args
()
videollava/eval/video/eval_benchmark_4_temporal.py:9
↓ 1 callersFunctionparse_args
()
videollava/eval/video/eval_video_qa.py:9
↓ 1 callersFunctionparse_args
()
videollava/eval/video/eval_benchmark_5_consistency.py:9
↓ 1 callersFunctionparse_args
()
videollava/eval/video/eval_benchmark_2_detailed_orientation.py:9
↓ 1 callersFunctionparse_args
()
videollava/eval/video/eval_benchmark_1_correctness.py:9
↓ 1 callersFunctionparse_score
(review)
videollava/eval/eval_gpt_review_bench.py:36
↓ 1 callersFunctionparse_score
(review)
videollava/eval/eval_gpt_review.py:39
↓ 1 callersFunctionparse_score
(review)
videollava/eval/eval_gpt_review_visual.py:36
↓ 1 callersFunctionpatch_tensor_constructor
(fn)
videollava/model/language_model/mpt/meta_init_context.py:76
↓ 1 callersFunctionprepare_input
(tokenizer, prompts)
videollava/eval/eval_mmlu.py:124
↓ 1 callersFunctionpreprocess_llama_2
( sources, tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False )
videollava/train/train.py:360
↓ 1 callersFunctionpreprocess_mpt
( sources, tokenizer: transformers.PreTrainedTokenizer, )
videollava/train/train.py:524
↓ 1 callersFunctionpreprocess_plain
( sources: Sequence[str], tokenizer: transformers.PreTrainedTokenizer, )
videollava/train/train.py:590
↓ 1 callersFunctionpreprocess_v1
( sources, tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False )
videollava/train/train.py:442
↓ 1 callersFunctionpretty_print_semaphore
(semaphore)
videollava/utils.py:138
↓ 1 callersMethodprocess_digit_article
(self, in_text)
videollava/eval/m4c_evaluator.py:198
↓ 1 callersMethodprocess_punctuation
(self, in_text)
videollava/eval/m4c_evaluator.py:186
↓ 1 callersFunctionprompt_processor
(prompt)
videollava/eval/eval_textvqa.py:17
↓ 1 callersMethodreceive_heart_beat
(self, worker_name: str, queue_length: int)
videollava/serve/controller.py:173
↓ 1 callersMethodrefresh_all_workers
(self)
videollava/serve/controller.py:104
↓ 1 callersMethodremove_stable_workers_by_expiration
(self)
videollava/serve/controller.py:183
↓ 1 callersFunctionreplace_llama_attn_with_flash_attn
()
videollava/train/llama_flash_attn_monkey_patch.py:105
↓ 1 callersFunctionreplace_llama_attn_with_xformers_attn
()
videollava/train/llama_xformers_attn_monkey_patch.py:19
↓ 1 callersMethodresize_pos
(self, m, vision_config)
videollava/model/multimodal_encoder/languagebind/audio/modeling_audio.py:795
↓ 1 callersMethodresize_pos
(self, m, vision_config)
videollava/model/multimodal_encoder/languagebind/depth/modeling_depth.py:795
↓ 1 callersMethodresize_pos
(self, m, vision_config)
videollava/model/multimodal_encoder/languagebind/thermal/modeling_thermal.py:795
↓ 1 callersFunctionrun_inference
Run inference on ActivityNet QA DataSet using the Video-ChatGPT model. Args: args: Command-line arguments.
videollava/eval/video/run_inference_video_qa_act.py:96
↓ 1 callersFunctionrun_inference
Run inference on a set of video files using the provided model. Args: args: Command-line arguments.
videollava/eval/video/run_inference_benchmark_consistency.py:36
↓ 1 callersFunctionrun_inference
Run inference on ActivityNet QA DataSet using the Video-ChatGPT model. Args: args: Command-line arguments.
videollava/eval/video/run_inference_video_qa.py:95
↓ 1 callersFunctionrun_inference
Run inference on a set of video files using the provided model. Args: args: Command-line arguments.
videollava/eval/video/run_inference_benchmark_general.py:36
↓ 1 callersFunctionsafe_save_model_for_hf_trainer
Collects the state dict and dump to disk.
videollava/train/train.py:192
↓ 1 callersFunctionsave_image_to_local
(image)
videollava/serve/gradio_web_server.py:19
↓ 1 callersFunctionsave_video_to_local
(video_path)
videollava/serve/gradio_web_server.py:27
↓ 1 callersFunctionsize
(c)
videollava/eval/eval_gqa.py:292
↓ 1 callersFunctionsmall_param_init_fn_
(module: nn.Module, n_layers: int, d_model: int, init_div_is_residual: Union[int, float, str, bool]=True, emb_
videollava/model/language_model/mpt/param_init_fns.py:137
↓ 1 callersFunctionsmart_tokenizer_and_embedding_resize
Resize tokenizer and embedding. Note: This is the unoptimized version that may make your embedding size not be divisible by 64.
videollava/train/train.py:231
← previousnext →201–300 of 670, ranked by callers