MCPcopy Create free account

hub / github.com/arctanxarc/MC-LLaVA / functions

Functions203 in github.com/arctanxarc/MC-LLaVA

⨍ Functions 203◇ Types & classes 35
↓ 16 callersFunctionprocess_images
(images, image_processor, model_cfg)
llava/mm_utils.py:166
↓ 8 callersMethodget_model
(self)
llava/model/llava_arch.py:134
↓ 7 callersFunctionget_model_name_from_path
(model_path)
llava/mm_utils.py:230
↓ 7 callersMethodget_prompt
(self)
llava/conversation.py:32
↓ 6 callersFunctionexpand2square
(pil_img, background_color)
llava/mm_utils.py:152
↓ 6 callersFunctionget_query
(args, query, model, sks_system_prompt=None)
llava/dataset.py:741
↓ 6 callersFunctionget_test_image_paths_by_concept
(dataset_root, concept_name)
llava/dataset.py:26
↓ 6 callersMethodget_vision_tower
(self)
llava/model/llava_arch.py:43
↓ 5 callersMethodcopy
(self)
llava/conversation.py:180
↓ 5 callersFunctiondisable_torch_init
Disable the redundant torch default initialization to accelerate model creation.
llava/utils.py:93
↓ 5 callersMethodgenerate
( self, inputs: Optional[torch.Tensor] = None, images: Optional[torch.Tensor] = None,
llava/model/language_model/llava_llama.py:103
↓ 5 callersFunctionget_test_multi_image_paths_by_concept
(dataset_root, concept_name)
llava/dataset.py:35
↓ 5 callersFunctionload_pretrained_model
(model_path, model_base, model_name, load_8bit=False, load_4bit=False, device_map="auto", device="cuda", use_f
llava/model/builder.py:28
↓ 5 callersMethodprepare_inputs_labels_for_multimodal
( self, input_ids, position_ids, attention_mask, past_key_values, labels, images, image_sizes=
llava/model/llava_arch.py:145
↓ 4 callersMethodappend_message
(self, role, message)
llava/conversation.py:109
↓ 4 callersFunctioncalculate_bleu
(reference, candidate)
eval/eval.py:60
↓ 4 callersFunctioncalculate_bleu
(reference, candidate)
eval/eval_w_som.py:63
↓ 4 callersMethodembed_tokens
(self, x)
llava/model/language_model/llava_mpt.py:36
↓ 4 callersFunctionget_model
(device, model_path=None, model_name=None, model_base=None)
eval/gen_som.py:31
↓ 4 callersFunctionget_test_image_paths_by_concept
(dataset_root, concept_name)
llava/dataset_som.py:28
↓ 4 callersMethodload_model
(self, device_map=None)
llava/model/multimodal_encoder/clip_encoder.py:24
↓ 4 callersFunctiontokenizer_image_token_batch
(prompts, tokenizer, image_token_index=IMAGE_TOKEN_INDEX, return_tensors=None, return_labels=True)
llava/mm_utils.py:206
↓ 3 callersMethodfeature_select
(self, image_forward_outs)
llava/model/multimodal_encoder/clip_encoder.py:35
↓ 3 callersFunctionget_test_multi_image_paths_by_concept
(dataset_root, concept_name)
llava/dataset_som.py:37
↓ 3 callersMethodget_vision_tower
(self)
llava/model/llava_arch.py:137
↓ 2 callersFunctionauto_upgrade
(config)
llava/model/utils.py:4
↓ 2 callersFunctionbuild_vision_projector
(config, delay_load=False, **kwargs)
llava/model/multimodal_projector/builder.py:33
↓ 2 callersFunctionbuild_vision_tower
(vision_tower_cfg, **kwargs)
llava/model/multimodal_encoder/builder.py:5
↓ 2 callersMethodencode_images
(self, images)
llava/model/llava_arch.py:140
↓ 2 callersFunctionget_embeddings
(image_tensor, model, when2cls='mm')
eval/gen_som.py:85
↓ 2 callersFunctionget_test_image_paths_by_concept_for_neg
(dataset_root, concept_name)
llava/dataset_som.py:54
↓ 2 callersFunctionget_test_multi_image_paths_by_concept_for_neg
(dataset_root, concept_name)
llava/dataset_som.py:63
↓ 2 callersMethodprocess_image
(self, image, image_process_mode, return_pil=False, image_format='PNG', max_len=1344, min_len=672)
llava/conversation.py:112
↓ 2 callersFunctionselect_best_resolution
Selects the best resolution from a list of possible resolutions based on the original size. Args: original_size (tuple): The origina
llava/mm_utils.py:12
↓ 1 callersMethod__init__
(self, config: LlamaConfig)
llava/model/language_model/llava_llama.py:35
↓ 1 callersMethod__init__
(self, config: MptConfig)
llava/model/language_model/llava_mpt.py:32
↓ 1 callersMethod__init__
(self, config: MistralConfig)
llava/model/language_model/llava_mistral.py:38
↓ 1 callersMethod__init__
(self)
llava/model/multimodal_projector/builder.py:7
↓ 1 callersMethod__init__
(self, vision_tower, args, delay_load=False)
llava/model/multimodal_encoder/clip_encoder.py:8
↓ 1 callersFunctionanalyze_caption
(conv_types, preds, gts)
eval/eval.py:155
↓ 1 callersFunctionanalyze_caption
(conv_types, preds, gts)
eval/eval_w_som.py:167
↓ 1 callersFunctionanalyze_choice
(conv_types, preds, gts)
eval/eval.py:109
↓ 1 callersFunctionanalyze_choice
(conv_types, preds, gts)
eval/eval_w_som.py:122
↓ 1 callersFunctionanalyze_rec
(conv_types, preds, gts)
eval/eval.py:72
↓ 1 callersFunctionanalyze_rec
(conv_types, preds, gts)
eval/eval_w_som.py:75
↓ 1 callersFunctionanalyze_text_choice
(conv_types, preds, gts)
eval/eval.py:125
↓ 1 callersFunctionanalyze_text_choice
(conv_types, preds, gts)
eval/eval_w_som.py:138
↓ 1 callersFunctionanalyze_vqa
(conv_types, preds, gts)
eval/eval.py:139
↓ 1 callersFunctionanalyze_vqa
(conv_types, preds, gts)
eval/eval_w_som.py:152
↓ 1 callersFunctionanalyze_yo_rec
(preds, gts)
eval/eval_w_som.py:111
↓ 1 callersFunctionapply_delta
(base_model_path, target_model_path, delta_path)
llava/model/apply_delta.py:13
↓ 1 callersMethodcall_for_batch
(self, output_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs)
llava/mm_utils.py:253
↓ 1 callersFunctionconsolidate_ckpt
(src_path, dst_path)
llava/model/consolidate.py:13
↓ 1 callersFunctioncontrasting_color
(rgb)
eval/gen_som.py:46
↓ 1 callersFunctiondivide_to_patches
Divides an image into patches of a specified size. Args: image (PIL.Image.Image): The input image. patch_size (int): The siz
llava/mm_utils.py:77
↓ 1 callersFunctiondraw_numbers_on_image
(ax, number_coords, font_size=DEFAULT_FONT_SIZE, color="g")
eval/gen_som.py:68
↓ 1 callersFunctiondraw_text
(ax, text, position, *, font_size=None, color="g", horizontal_alignment="center", rotation=0)
eval/gen_som.py:39
↓ 1 callersFunctiongenerate_convosation4concept
(root_dir, concept, out_put_root_dir)
llava/build_qa.py:127
↓ 1 callersFunctiongenerate_joint_qa_pairs
(root_dir, concept_names, template_file, out_put_root_dir, num_qa_pairs=10)
llava/build_qa.py:168
↓ 1 callersFunctiongenerate_negative_qa_pairs4concept
(random_images, concept, root_dir, templates, out_put_root_dir, num_qa_pairs=100)
llava/build_qa.py:49
↓ 1 callersFunctiongenerate_positive_qa_pairs4concept
(root_dir, concept, templates, out_put_root_dir, num_qa_pairs=5)
llava/build_qa.py:6
↓ 1 callersFunctiongenerate_strong_negtive_qa_pairs4concept
(concept, root_dir, templates, out_put_root_dir, data_size, seed = 0)
llava/build_qa.py:77
↓ 1 callersFunctionget_anyres_image_grid_shape
Calculate the shape of the image patch grid after the preprocessing for images of any resolution. Args: image_size (tuple): The size
llava/mm_utils.py:99
↓ 1 callersFunctionget_embeddings
(image_tensor, model, when2cls='mm')
train/train_joint.py:84
↓ 1 callersMethodget_images
(self, return_pil=False)
llava/conversation.py:152
↓ 1 callersFunctionget_logger
(filename, verbosity=1, name=None)
train/train_joint.py:64
↓ 1 callersMethodget_model
(self)
llava/model/language_model/llava_llama.py:52
↓ 1 callersMethodget_model
(self)
llava/model/language_model/llava_mistral.py:54
↓ 1 callersFunctionget_model_
(model_path)
llava/dataset_som.py:948
↓ 1 callersFunctionget_model_
(model_path)
llava/dataset.py:730
↓ 1 callersFunctionget_test_args
()
eval/eval.py:18
↓ 1 callersFunctionget_test_args
()
eval/gen_som.py:22
↓ 1 callersFunctionget_test_args
()
eval/eval_w_som.py:18
↓ 1 callersFunctionget_train_args
()
train/train_joint.py:19
↓ 1 callersFunctioninsert_separator
(X, sep)
llava/mm_utils.py:188
↓ 1 callersFunctionload_from_hf
(repo_id, filename, subfolder=None)
llava/model/builder.py:71
↓ 1 callersFunctionload_image
(image_file)
llava/dataset_som.py:921
↓ 1 callersFunctionload_image
(image_file)
llava/dataset.py:703
↓ 1 callersFunctionload_trained_weights
(model, tokenizer, checkpoint_path, sks_names, ckpt_name, epoch2load=14, prefix_token_count=16)
eval/eval.py:35
↓ 1 callersFunctionload_trained_weights
(model, tokenizer, checkpoint_path, sks_names, ckpt_name, epoch2load=11, prefix_token_count=16)
eval/eval_w_som.py:35
↓ 1 callersFunctionmain
(args)
eval/eval.py:186
↓ 1 callersFunctionmain
()
eval/gen_som.py:138
↓ 1 callersFunctionmain
(args)
eval/eval_w_som.py:198
↓ 1 callersFunctionmain
(args)
train/train_joint.py:109
↓ 1 callersFunctionmake_delta
(base_model_path, target_model_path, delta_path, hub_repo_id)
llava/model/make_delta.py:13
↓ 1 callersFunctionprocess_anyres_image
Process an image with variable resolutions. Args: image (PIL.Image.Image): The input image to be processed. processor: The i
llava/mm_utils.py:119
↓ 1 callersFunctionprocess_masks
(masks)
eval/gen_som.py:73
↓ 1 callersFunctionprocess_masks
(masks)
train/train_joint.py:97
↓ 1 callersFunctionresize_and_pad_image
Resize and pad an image to a target resolution while maintaining aspect ratio. Args: image (PIL.Image.Image): The input image.
llava/mm_utils.py:42
↓ 1 callersFunctiontokenizer_image_token
(prompt, tokenizer, image_token_index=IMAGE_TOKEN_INDEX, return_tensors=None)
llava/mm_utils.py:185
↓ 1 callersFunctionunpad_image
Unpads a PyTorch tensor of a padded and resized image. Args: tensor (torch.Tensor): The image tensor, assumed to be in CxHxW format.
llava/model/llava_arch.py:100
Method__call__
(self, output_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs)
llava/mm_utils.py:266
Method__getattr__
(self, attr)
llava/utils.py:70
Method__getitem__
(self, i)
llava/dataset_som.py:155
Method__getitem__
(self, i)
llava/dataset_som.py:235
Method__getitem__
(self, i)
llava/dataset_som.py:374
Method__getitem__
(self, i)
llava/dataset_som.py:521
Method__getitem__
(self, i)
llava/dataset_som.py:632
Method__getitem__
(self, i)
llava/dataset_som.py:698
Method__getitem__
(self, i)
llava/dataset_som.py:782
next →1–100 of 203, ranked by callers