MCPcopy Create free account

hub / github.com/X-PLUG/mPLUG-Owl / functions

Functions946 in github.com/X-PLUG/mPLUG-Owl

⨍ Functions 946◇ Types & classes 168↳ Endpoints 11
↓ 1 callersFunctionbuild_from_cfg
Build a module from config dict when it is a class configuration, or call a function from config dict when it is a function configuration. Ex
mPLUG-Owl/pipeline/data_utils/registry.py:92
↓ 1 callersMethodbuild_submission
(self, merged_outputs, saver)
mPLUG-Owl3/evaluation/tasks/task_define/vqa.py:234
↓ 1 callersFunctionbuild_train_valid_test_datasets
(input_file, tokenizer, max_length=80, config=None)
mPLUG-Owl/pipeline/data_utils/__init__.py:16
↓ 1 callersFunctioncalculate_confusion_matrix
(predicted_labels, ground_truth)
mPLUG-Owl3/evaluation/tasks/task_define/vqa.py:422
↓ 1 callersFunctioncalculate_metric
(results)
mPLUG-Owl3/evaluation/tasks/task_define/mmbench.py:102
↓ 1 callersFunctioncalculate_metric
(results)
mPLUG-Owl3/evaluation/tasks/task_define/qbench.py:54
↓ 1 callersFunctioncalculate_metrics_from_lists
(predicted_labels, ground_truth)
mPLUG-Owl3/evaluation/tasks/task_define/vqa.py:435
↓ 1 callersFunctioncheck_answer
(predict, gt_answer)
mPLUG-Owl3/evaluation/tasks/task_define/next_qa.py:488
↓ 1 callersFunctioncheck_is_number
Check if the given string a number.
mPLUG-Owl2/mplug_owl2/evaluate/evaluate_mmmu.py:127
↓ 1 callersFunctioncheck_is_number
Check if the given string a number.
mPLUG-Owl3/evaluation/tasks/task_define/qbench.py:236
↓ 1 callersMethodcompute_metric
(self, gts, preds)
mPLUG-Owl2/mplug_owl2/evaluate/evaluate_mme.py:61
↓ 1 callersMethodcopy
(self, src, dst)
mPLUG-Owl/serve/io_utils.py:237
↓ 1 callersFunctioncount_video_frames
(_context)
mPLUG-Owl3/gradio_demo.py:245
↓ 1 callersFunctiondebug
()
mPLUG-Owl3/gradio_demo.py:5
↓ 1 callersFunctiondecode_base64_to_image
(base64_string)
mPLUG-Owl2/mplug_owl2/evaluate/mmbench_converter.py:15
↓ 1 callersMethoddeprecated_register_module
(self, cls=None, force=False)
mPLUG-Owl3/evaluation/tasks/task_define/registry.py:358
↓ 1 callersMethoddeprecated_register_module
(self, cls=None, force=False)
mPLUG-Owl/pipeline/data_utils/registry.py:358
↓ 1 callersFunctiondisable_torch_init
Disable the redundant torch default initialization to accelerate model creation.
mPLUG-Owl2/mplug_owl2/serve/cli.py:17
↓ 1 callersFunctiondo_generate
The interface for generation Args: prompts (List[str]): The prompt text image_list (List[str]): Paths of images model (Mp
mPLUG-Owl/pipeline/interface.py:32
↓ 1 callersFunctioneasy_name
(parent_dir, child_name)
mPLUG-Owl3/evaluation/tasks/task_define/base.py:130
↓ 1 callersFunctionempty_image
()
mPLUG-Owl3/evaluation/tasks/task_define/base.py:45
↓ 1 callersFunctionencode_message
(_question)
mPLUG-Owl3/gradio_demo.py:213
↓ 1 callersFunctionencode_mm_file
(mm_file)
mPLUG-Owl3/gradio_demo.py:202
↓ 1 callersFunctionencode_video
(video)
mPLUG-Owl3/gradio_demo.py:169
↓ 1 callersFunctioneval_multi_choice
Evaluate a multiple choice instance.
mPLUG-Owl2/mplug_owl2/evaluate/evaluate_mmmu.py:237
↓ 1 callersFunctioneval_multi_choice
Evaluate a multiple choice instance.
mPLUG-Owl3/evaluation/tasks/task_define/qbench.py:344
↓ 1 callersFunctioneval_open
Evaluate an open question instance
mPLUG-Owl2/mplug_owl2/evaluate/evaluate_mmmu.py:253
↓ 1 callersFunctioneval_open
Evaluate an open question instance
mPLUG-Owl3/evaluation/tasks/task_define/qbench.py:360
↓ 1 callersFunctionevaluate
Batch evaluation for multiple choice and open questions.
mPLUG-Owl2/mplug_owl2/evaluate/evaluate_mmmu.py:281
↓ 1 callersMethodevaluate
(self, quesIds=None)
mPLUG-Owl3/evaluation/vqa_utils/vqa_eval.py:193
↓ 1 callersMethodevaluate
(self, merged_outputs, results_file, submission_file)
mPLUG-Owl3/evaluation/tasks/task_define/vqa.py:237
↓ 1 callersMethodevaluate
( self, pixel_values=None, input_ids=None, temperature=1.0, top_p=0.9
mPLUG-Owl/serve/model_worker.py:62
↓ 1 callersMethodevaluate_multi_choice_image
(self,preditions)
mPLUG-Owl3/evaluation/tasks/task_define/llava_interleave_bench.py:169
↓ 1 callersMethodevaluate_multichoice
(self, preditions)
mPLUG-Owl3/evaluation/tasks/task_define/llava_interleave_bench.py:157
↓ 1 callersFunctionevaluate_relaxed_accuracy
(entries)
mPLUG-Owl3/evaluation/tasks/task_define/vqa.py:395
↓ 1 callersMethodevaluate_rouge
(self,preds)
mPLUG-Owl3/evaluation/tasks/task_define/llava_interleave_bench.py:195
↓ 1 callersFunctionextract_answer
(model_output, options)
mPLUG-Owl3/evaluation/tasks/task_define/mmbench.py:87
↓ 1 callersMethodextract_characters_regex
(self, s)
mPLUG-Owl3/evaluation/tasks/task_define/next_qa.py:331
↓ 1 callersFunctionextract_numbers
Exact all forms of numbers from a string with regex.
mPLUG-Owl2/mplug_owl2/evaluate/evaluate_mmmu.py:162
↓ 1 callersFunctionextract_numbers
Exact all forms of numbers from a string with regex.
mPLUG-Owl3/evaluation/tasks/task_define/qbench.py:271
↓ 1 callersFunctionfewshot_respond
(_image, _user_message, _chat_bot, _app_cfg, params_form)
mPLUG-Owl3/gradio_demo.py:328
↓ 1 callersFunctionfind_all_linear_names
(model)
mPLUG-Owl2/mplug_owl2/train/train.py:158
↓ 1 callersMethodflush
(self)
mPLUG-Owl2/mplug_owl2/utils.py:87
↓ 1 callersMethodflush
Dummy method for compatibility.
mPLUG-Owl/serve/io_utils.py:372
↓ 1 callersMethodfrom_str
(cls, name)
mPLUG-Owl2/mplug_owl2/serve/controller.py:33
↓ 1 callersMethodgenerate_stream
(self, params)
mPLUG-Owl2/mplug_owl2/serve/model_worker.py:123
↓ 1 callersMethodgenerate_stream
(self, params)
mPLUG-Owl2/mplug_owl2/local_serve/model_worker.py:50
↓ 1 callersMethodgenerate_stream_gate
(self, params)
mPLUG-Owl2/mplug_owl2/serve/model_worker.py:192
↓ 1 callersMethodgenerate_stream_gate
(self, params)
mPLUG-Owl2/mplug_owl2/local_serve/model_worker.py:119
↓ 1 callersFunctiongenerate_submission_file
(results, raw_annotation)
mPLUG-Owl2/mplug_owl2/evaluate/evaluate_mmbench.py:69
↓ 1 callersFunctiongenerate_submission_file
(results, raw_annotation)
mPLUG-Owl3/evaluation/tasks/task_define/mmbench.py:143
↓ 1 callersFunctionget_2d_sincos_pos_embed_from_grid
(embed_dim, grid)
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:52
↓ 1 callersFunctionget_abs_pos
(abs_pos, tgt_size)
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:14
↓ 1 callersFunctionget_args
()
mPLUG-Owl3/evaluation/tasks/general_task_pipeline2.py:136
↓ 1 callersFunctionget_args
()
mPLUG-Owl/pipeline/utils.py:20
↓ 1 callersMethodget_decoder
(self)
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:1245
↓ 1 callersMethodget_decoder
(self)
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:1159
↓ 1 callersMethodget_encoder
(self)
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:1242
↓ 1 callersMethodget_encoder
(self)
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:1156
↓ 1 callersMethodget_extended_attention_mask
Makes broadcastable attention and causal masks so that future and masked tokens are ignored. Arguments: attention_mask (
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:800
↓ 1 callersMethodget_extended_attention_mask
Makes broadcastable attention and causal masks so that future and masked tokens are ignored. Arguments: attention_mask (
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:1032
↓ 1 callersMethodget_extended_attention_mask
Makes broadcastable attention and causal masks so that future and masked tokens are ignored. Arguments: attention_mask (
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:967
↓ 1 callersFunctionget_frame_indices_start_end
(num_frames, vlen, fps, start_time, end_time)
mPLUG-Owl3/evaluation/tasks/task_define/video_utils.py:72
↓ 1 callersFunctionget_index
(num_frames, num_segments)
mPLUG-Owl/mplug_owl_video/processing_mplug_owl.py:14
↓ 1 callersMethodget_index
(self, num_frames, num_segments)
mPLUG-Owl/serve/conversation.py:58
↓ 1 callersFunctionget_key_subresponses
(response)
mPLUG-Owl2/mplug_owl2/evaluate/evaluate_mmmu.py:190
↓ 1 callersFunctionget_key_subresponses
(response)
mPLUG-Owl3/evaluation/tasks/task_define/qbench.py:299
↓ 1 callersFunctionget_ltor_masks_and_position_ids_from_embeddings
Build masks and position id for left to right model.
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:96
↓ 1 callersFunctionget_ltor_masks_and_position_ids_from_embeddings
Build masks and position id for left to right model.
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:90
↓ 1 callersFunctionget_modality_length_grouped_indices
(lengths, batch_size, world_size, generator=None)
mPLUG-Owl2/mplug_owl2/train/mplug_owl2_trainer.py:60
↓ 1 callersFunctionget_model
Model Provider with tokenizer and processor. Args: pretrained_ckpt (string): The path to pre-trained checkpoint. use_bf16 (bool,
mPLUG-Owl/pipeline/interface.py:10
↓ 1 callersMethodget_output_embeddings
(self)
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:1004
↓ 1 callersMethodget_output_embeddings
(self)
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:1239
↓ 1 callersMethodget_output_embeddings
(self)
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:1153
↓ 1 callersFunctionget_peft_state_maybe_zero_3
(named_params, bias)
mPLUG-Owl2/mplug_owl2/train/train.py:119
↓ 1 callersFunctionget_peft_state_non_lora_maybe_zero_3
(named_params, require_grad_only=True)
mPLUG-Owl2/mplug_owl2/train/train.py:144
↓ 1 callersMethodget_random_ops
(self)
mPLUG-Owl/pipeline/data_utils/randaugment.py:323
↓ 1 callersFunctionget_tokenize_len
(prompts)
mPLUG-Owl2/mplug_owl2/train/train.py:424
↓ 1 callersMethodinfer_scope
Infer the scope of registry. The name of the package where registry is defined will be returned. Example: >>> # in mmdet
mPLUG-Owl3/evaluation/tasks/task_define/registry.py:230
↓ 1 callersMethodinfer_scope
Infer the scope of registry. The name of the package where registry is defined will be returned. Example: >>> # in mmdet
mPLUG-Owl/pipeline/data_utils/registry.py:230
↓ 1 callersMethodinfo
Print information about the VQA annotation file. :return:
mPLUG-Owl3/evaluation/vqa_utils/vqa.py:71
↓ 1 callersFunctioninit
()
mPLUG-Owl/serve/serve_utils.py:39
↓ 1 callersFunctioninitialize_distributed
Initialize torch.distributed and core model parallel.
mPLUG-Owl3/evaluation/tasks/general_task_pipeline2.py:38
↓ 1 callersFunctioninsert_separator
(X, sep)
mPLUG-Owl2/mplug_owl2/mm_utils.py:56
↓ 1 callersFunctionis_image
(filename)
mPLUG-Owl3/gradio_demo.py:73
↓ 1 callersFunctionis_seq_of
Check whether it is a sequence of some type. Args: seq (Sequence): The sequence to be checked. expected_type (type): Expected type
mPLUG-Owl3/evaluation/tasks/task_define/registry.py:11
↓ 1 callersFunctionis_seq_of
Check whether it is a sequence of some type. Args: seq (Sequence): The sequence to be checked. expected_type (type): Expected type
mPLUG-Owl/pipeline/data_utils/registry.py:11
↓ 1 callersFunctionis_video
(filename)
mPLUG-Owl3/gradio_demo.py:76
↓ 1 callersMethodisdir
(self, path)
mPLUG-Owl/serve/io_utils.py:313
↓ 1 callersMethodisfile
(self, path)
mPLUG-Owl/serve/io_utils.py:318
↓ 1 callersMethodislocal
(self, path: str)
mPLUG-Owl/serve/io_utils.py:66
↓ 1 callersMethodjudge_multi_choice
(self,sample)
mPLUG-Owl3/evaluation/tasks/task_define/llava_interleave_bench.py:140
↓ 1 callersMethodlast_modified
(self, path: str)
mPLUG-Owl/serve/io_utils.py:54
↓ 1 callersMethodlist_models
(self)
mPLUG-Owl2/mplug_owl2/serve/controller.py:112
↓ 1 callersMethodloadRes
Load result file and return a result object. :param resFile (str) : file name of result file :return: res (obj)
mPLUG-Owl3/evaluation/vqa_utils/vqa.py:173
↓ 1 callersFunctionload_from_hf
(repo_id, filename, subfolder=None)
mPLUG-Owl2/mplug_owl2/model/builder.py:68
↓ 1 callersFunctionload_image
(image_file)
mPLUG-Owl2/mplug_owl2/serve/cli.py:26
↓ 1 callersFunctionload_jsonl
(filename)
mPLUG-Owl/pipeline/data_utils/xgpt3_dataset.py:33
↓ 1 callersFunctionload_video
(path, num_frames=4)
mPLUG-Owl/mplug_owl_video/processing_mplug_owl.py:22
↓ 1 callersMethodload_video
(self, path, num_frames=4)
mPLUG-Owl/serve/conversation.py:66
← previousnext →201–300 of 946, ranked by callers