MCPcopy Create free account

hub / github.com/boheumd/MA-LMM / functions

Functions1,238 in github.com/boheumd/MA-LMM

⨍ Functions 1,238◇ Types & classes 310↳ Endpoints 9
↓ 1 callersFunctiondownload_datasets
(root, url)
lavis/datasets/download_scripts/download_coco.py:29
↓ 1 callersFunctiondownload_datasets
(root, url)
lavis/datasets/download_scripts/download_gqa.py:24
↓ 1 callersFunctiondownload_datasets
(root, url)
lavis/datasets/download_scripts/download_vg.py:27
↓ 1 callersFunctiondownload_datasets
Download the Imagenet-R dataset archives and expand them in the folder provided as parameter
lavis/datasets/download_scripts/download_didemo.py:23
↓ 1 callersFunctiondownload_datasets
(root, url)
lavis/datasets/download_scripts/download_msvd.py:24
↓ 1 callersMethodevaluate
(self, quesIds=None)
lavis/common/vqa_tools/vqa_eval.py:193
↓ 1 callersMethodevaluation
(self, model, data_loader, cuda_enabled=True)
lavis/tasks/base_task.py:83
↓ 1 callersFunctionextract_archive
Extract archive. Args: from_path: the path of the archive. to_path: the root path of the extracted files (directory of from_path)
lavis/datasets/data_utils.py:178
↓ 1 callersFunctionextract_frames
(video_name)
data/extract_frames.py:21
↓ 1 callersFunctionfetch_requirements
(filename)
setup.py:16
↓ 1 callersFunctionfetch_single_image
(image_url, timeout=None, retries=0)
lavis/datasets/download_scripts/download_sbu.py:28
↓ 1 callersMethodfix_init_weight
(self)
lavis/models/eva_vit.py:303
↓ 1 callersFunctionformat_text
(text)
app/dataset_browser.py:88
↓ 1 callersMethodforward
(self, x)
lavis/models/vit.py:45
↓ 1 callersMethodforward
Forward function for training and evaluation. Args: samples (dict): a dict of input samples, which contains the followin
lavis/models/blip_models/blip_nlvr.py:56
↓ 1 callersMethodforward
(self, samples, is_train=True)
lavis/models/blip_models/blip_classification.py:77
↓ 1 callersMethodforward
(self, samples, is_train=True)
lavis/models/albef_models/albef_classification.py:83
↓ 1 callersMethodforward
Forward function for training and evaluation. Args: samples (dict): a dict of input samples, which contains the followin
lavis/models/albef_models/albef_nlvr.py:79
↓ 1 callersMethodforward_decoder
(self, samples, encoder_out, **kwargs)
lavis/models/blip_models/blip_vqa.py:123
↓ 1 callersMethodforward_decoder
(self, samples, image_embeds)
lavis/models/blip_models/blip_caption.py:57
↓ 1 callersMethodforward_decoder
(self, samples, encoder_out, **kwargs)
lavis/models/albef_models/albef_vqa.py:167
↓ 1 callersMethodforward_features
(self, x)
lavis/models/eva_vit.py:327
↓ 1 callersMethodforward_image
(self, image)
lavis/models/blip2_models/blip2_qformer.py:323
↓ 1 callersFunctiongather_features
( image_features, text_features, local_loss=False, gather_with_grad=False, rank=0, wor
lavis/models/clip_models/loss.py:20
↓ 1 callersFunctiongather_items
(samples, exclude=[])
app/dataset_browser.py:69
↓ 1 callersMethodgenerate
Args: samples (dict): A dictionary containing the following keys: - image (torch.Tensor): A tensor of shape (batc
lavis/models/blip_models/blip_caption.py:136
↓ 1 callersMethodgenerate
( self, samples, use_nucleus_sampling=False, num_beams=5, max_length=2
lavis/models/blip2_models/blip2_t5_instruct.py:280
↓ 1 callersMethodgenerate
( self, samples, use_nucleus_sampling=False, num_beams=5, max_length=2
lavis/models/blip2_models/blip2_vicuna_instruct.py:313
↓ 1 callersFunctiongenerate_caption
( model, image, use_nucleus_sampling=False, num_beams=3, max_length=40, min_length=5 )
app/caption.py:72
↓ 1 callersMethodgenerate_from_encoder
( self, tokenized_prompt, visual_embeds, sep_token_id, pad_token_id,
lavis/models/med.py:1316
↓ 1 callersMethodget_attention_map
(self)
lavis/models/vit.py:85
↓ 1 callersMethodget_attention_map
(self)
lavis/models/blip_models/nlvr_encoder.py:137
↓ 1 callersMethodget_attn_gradients
(self)
lavis/models/vit.py:79
↓ 1 callersMethodget_attn_gradients
(self)
lavis/models/blip_models/nlvr_encoder.py:131
↓ 1 callersFunctionget_cached_file_path
()
lavis/common/dist_utils.py:123
↓ 1 callersFunctionget_dist_info
()
lavis/common/dist_utils.py:93
↓ 1 callersMethodget_extended_attention_mask
Makes broadcastable attention and causal masks so that future and masked tokens are ignored. Arguments: attention_mask (
lavis/models/med.py:754
↓ 1 callersMethodget_extended_attention_mask
Makes broadcastable attention and causal masks so that future and masked tokens are ignored. Arguments: attention_mask (
lavis/models/blip_models/nlvr_encoder.py:714
↓ 1 callersMethodget_lr_scheduler_class
(cls, name)
lavis/common/registry.py:248
↓ 1 callersMethodget_random_ops
(self)
lavis/processors/randaugment.py:336
↓ 1 callersMethodget_random_ops
(self)
lavis/processors/randaugment.py:363
↓ 1 callersFunctionget_redirected_url
Given a URL, returns the URL it redirects to or the original URL in case of no indirection
lavis/common/utils.py:78
↓ 1 callersFunctionget_runner_class
Get runner class from config. Default to epoch-based runner.
train.py:64
↓ 1 callersMethodget_runner_class
(cls, name)
lavis/common/registry.py:252
↓ 1 callersMethodget_task_class
(cls, name)
lavis/common/registry.py:240
↓ 1 callersFunctionget_visual_key
(dataset)
app/dataset_browser.py:58
↓ 1 callersMethodglobal_avg
(self)
lavis/common/logger.py:111
↓ 1 callersMethodinit_parameters
(self)
lavis/models/clip_models/model.py:204
↓ 1 callersMethodinit_parameters
(self)
lavis/models/clip_models/model.py:516
↓ 1 callersFunctioninterpolate_pos_embed
(model, state_dict, interpolation: str = 'bicubic', seq_dim=1)
lavis/models/clip_vit.py:197
↓ 1 callersFunctioninterpolate_pos_embed
(model, checkpoint_model)
lavis/models/eva_vit.py:380
↓ 1 callersMethodlemmatizer
(self)
lavis/models/blip2_models/blip2_t5_instruct.py:715
↓ 1 callersMethodlemmatizer
(self)
lavis/models/blip2_models/blip2_t5.py:331
↓ 1 callersMethodlemmatizer
(self)
lavis/models/blip2_models/blip2_vicuna_instruct.py:776
↓ 1 callersMethodlemmatizer
(self)
lavis/models/blip2_models/blip2.py:330
↓ 1 callersMethodlist_lr_schedulers
(cls)
lavis/common/registry.py:272
↓ 1 callersFunctionlist_models
enumerate available model architectures based on config files
lavis/models/clip_models/model.py:1032
↓ 1 callersFunctionlist_openai_models
Returns the names of available CLIP models
lavis/models/clip_models/model.py:1045
↓ 1 callersFunctionlist_pretrained_tag_models
return all models having the specified pretrain tag
lavis/models/clip_models/pretrained.py:103
↓ 1 callersMethodlist_tasks
(cls)
lavis/common/registry.py:264
↓ 1 callersFunctionload_dataset_cache
(name)
app/dataset_browser.py:84
↓ 1 callersFunctionload_demo_image
(img_url=None)
app/classification.py:23
↓ 1 callersFunctionload_feat
()
app/multimodal_search.py:34
↓ 1 callersFunctionload_feature_extractor_model
(device)
app/multimodal_search.py:61
↓ 1 callersMethodload_from_pretrained
(self, url_or_filename)
lavis/models/albef_models/albef_vqa.py:381
↓ 1 callersFunctionload_openai_model
Load a CLIP model Parameters ---------- name : str A model name listed by `clip.available_models()`, or the path to a model checkp
lavis/models/clip_models/model.py:1050
↓ 1 callersFunctionload_preprocess
Load preprocessor configs and construct preprocessors. If no preprocessor is specified, return BaseProcessor, which does not do any preproce
lavis/models/__init__.py:124
↓ 1 callersFunctionload_state_dict
(checkpoint_path: str, map_location="cpu")
lavis/models/clip_models/model.py:923
↓ 1 callersMethodlock
(self, unlocked_groups=0, freeze_bn_stats=False)
lavis/models/clip_models/model.py:217
↓ 1 callersMethodloss
(self)
lavis/models/clip_models/model.py:501
↓ 1 callersFunctionmain
()
train.py:73
↓ 1 callersFunctionmain
()
evaluate.py:63
↓ 1 callersMethodmask
Prepare masked tokens inputs/labels for masked language modeling: 80% MASK, 10% random, 10% original.
lavis/models/albef_models/albef_pretrain.py:341
↓ 1 callersFunctionmerge_datasets
Merge datasets in download_path to storage_path
lavis/datasets/download_scripts/download_msrvtt.py:46
↓ 1 callersFunctionmove_directory
Move files from download_path to storage_path
lavis/datasets/download_scripts/download_flickr.py:32
↓ 1 callersFunctionmove_files
Move files from download_path to storage_path
lavis/datasets/download_scripts/download_didemo.py:31
↓ 1 callersFunctionmove_files
Move files from download_path to storage_path
lavis/datasets/download_scripts/download_msvd.py:28
↓ 1 callersFunctionnow
()
lavis/common/utils.py:35
↓ 1 callersFunctionopen_tsv
(fname, folder)
lavis/datasets/download_scripts/DownloadConceptualCaptions/download_data_cc3m.py:174
↓ 1 callersFunctionopen_tsv
(fname, folder)
lavis/datasets/download_scripts/DownloadConceptualCaptions/download_data_cc12m.py:174
↓ 1 callersFunctionparse_args
()
train.py:34
↓ 1 callersFunctionparse_args
()
evaluate.py:33
↓ 1 callersFunctionposterize_level_to_args
(MAX_LEVEL)
lavis/processors/randaugment.py:270
↓ 1 callersMethodpre_question
(self, question)
lavis/processors/blip_processors.py:90
↓ 1 callersMethodpredict
(self, samples)
lavis/models/clip_models/model.py:640
↓ 1 callersMethodprepare_few_shot_embeds
(self, samples)
lavis/models/blip2_models/blip2_t5_instruct.py:204
↓ 1 callersMethodprune_heads
(self, heads)
lavis/models/med.py:313
↓ 1 callersMethodprune_heads
(self, heads)
lavis/models/blip_models/nlvr_encoder.py:306
↓ 1 callersMethodprune_heads
(self, heads)
lavis/models/blip2_models/Qformer.py:299
↓ 1 callersMethodrank_answers
Generate the first token of answers using decoder and select ${num_ans_candidates} most probable ones. Then select answers from answe
lavis/models/albef_models/albef_vqa.py:269
↓ 1 callersFunctionread_and_process_images
(image_paths, vis_processor)
app/multimodal_search.py:183
↓ 1 callersFunctionread_img
(filepath)
app/utils.py:25
↓ 1 callersFunctionread_img
(filepath)
app/calculate_coco_features.py:31
↓ 1 callersFunctionrecord_cuda_stream
(batch)
lavis/datasets/datasets/dataloader_utils.py:114
↓ 1 callersMethodreset_queue_ptr
(self)
lavis/models/blip_models/blip_retrieval.py:357
↓ 1 callersMethodreset_queue_ptr
(self)
lavis/models/blip_models/blip_pretrain.py:362
↓ 1 callersFunctionresize
(clip, target_size, interpolation_mode)
lavis/processors/functional_video.py:33
↓ 1 callersFunctionresize_img
(raw_img)
app/utils.py:18
↓ 1 callersFunctionresize_img
(req)
lavis/datasets/download_scripts/DownloadConceptualCaptions/download_data_cc3m.py:124
↓ 1 callersFunctionresize_img
(req)
lavis/datasets/download_scripts/DownloadConceptualCaptions/download_data_cc12m.py:124
← previousnext →301–400 of 1,238, ranked by callers