MCPcopy Create free account

hub / github.com/alipay/Ant-Multi-Modal-Framework / functions

Functions4,004 in github.com/alipay/Ant-Multi-Modal-Framework

⨍ Functions 4,004◇ Types & classes 941↳ Endpoints 1
↓ 1 callersFunctionpatch_config
(config)
prj/Pink/pink/eval/model_gqa.py:66
↓ 1 callersFunctionpatch_config
(config)
prj/Pink/pink/eval/model_okvqa.py:65
↓ 1 callersFunctionpatch_config
(config)
prj/Pink/pink/eval/model_v7wgrounding.py:54
↓ 1 callersFunctionpatch_config
(config)
prj/Pink/pink/eval/model_iconqa.py:101
↓ 1 callersFunctionpatch_torch_scale_with_flash_attn
()
prj/M2_Encoder/vlmo/utils/patch_utils.py:102
↓ 1 callersFunctionpercentage_rechange
(json_dir, threshold, group_split_list, rank_top_k, json_save_dir, VTM_save_dir, csv_save_dir)
prj/snps3_vtp/auxiliary_files/generate_ss_word_json/3rd_get_json_csv_reprocess.py:48
↓ 1 callersFunctionplot_one_box
(x, img, color=None, label=None, line_thickness=None)
antmmf/utils/visual_utils/vis_utils.py:14
↓ 1 callersFunctionpoisson_noise
Add poisson noise to img. @param img: ndarray, Input image data on range[0,255]. @returns out : ndarray Output inte
antmmf/utils/dataset_utils.py:223
↓ 1 callersFunctionpool_processes
(processes, cmd)
antmmf/utils/launch.py:199
↓ 1 callersFunctionposterize_level_to_args
(MAX_LEVEL)
prj/M2_Encoder/vlmo/transforms/randaugment.py:249
↓ 1 callersFunctionpredict
(_chatbot, task_history, bbox_state)
prj/Pink/demo.py:115
↓ 1 callersMethodpredict
Args: data: image bytes json_obj: one json object include multimodal info Returns: Report(Ordere
antmmf/predictors/base_predictor.py:230
↓ 1 callersMethodpredict_for_evalai
(self, dataset_type)
antmmf/trainers/base_trainer.py:937
↓ 1 callersMethodprepare
(self, predictions, iou_type)
antmmf/modules/metrics/evaluators/coco_eval.py:76
↓ 1 callersMethodprepare_batch
Can be possibly overriden in your child class Prepare batch for passing to model. Whatever returned from here will be direct
antmmf/datasets/base_dataset.py:76
↓ 1 callersMethodprepare_feature
(self, image_feature, image_info)
antmmf/datasets/features/feature_readers.py:181
↓ 1 callersMethodprepare_for_coco_detection
(self, predictions)
antmmf/modules/metrics/evaluators/coco_eval.py:86
↓ 1 callersMethodprepare_for_coco_keypoint
(self, predictions)
antmmf/modules/metrics/evaluators/coco_eval.py:147
↓ 1 callersMethodprepare_for_coco_segmentation
(self, predictions)
antmmf/modules/metrics/evaluators/coco_eval.py:110
↓ 1 callersMethodpreprocess_item
(self, item)
prj/snps3_vtp/roi_univl/univl/pretrain_video_text/dataset.py:87
↓ 1 callersMethodpreprocess_item
(self, item)
prj/dmae_vtp/roi_univl/univl/pretrain_video_text/dataset.py:87
↓ 1 callersMethodpreprocess_item
(self, item)
prj/base_vtp/roi_univl/univl/pretrain_video_text/dataset.py:87
↓ 1 callersMethodpreprocess_item
(self, item)
prj/cnvid_vtp/roi_univl/univl/pretrain_video_text/dataset.py:87
↓ 1 callersMethodpreprocess_item
(self, item)
antmmf/datasets/database/annotated.py:160
↓ 1 callersMethodpreprocess_target
:param target: :return:
antmmf/datasets/processors/image_processors.py:634
↓ 1 callersFunctionpretty_print
Print the configuration in a pretty way. Args: config (Configuration): which must include the default configurations which s
antmmf/common/configuration.py:645
↓ 1 callersMethodprocessDigitArticle
(self, inText)
prj/Pink/pink/eval/vqa_tools/vqa_result.py:278
↓ 1 callersMethodprocessDigitArticle
(self, inText)
prj/Pink/pink/eval/vqa_tools/vqa_eval.py:261
↓ 1 callersMethodprocess_annotation
(self, annotation_database)
prj/snps3_vtp/roi_univl/univl/pretrain_video_text/dataset.py:41
↓ 1 callersMethodprocess_annotation
(self, annotation_database)
prj/dmae_vtp/roi_univl/univl/pretrain_video_text/dataset.py:41
↓ 1 callersMethodprocess_annotation
(self, annotation_database)
prj/base_vtp/roi_univl/univl/pretrain_video_text/dataset.py:41
↓ 1 callersMethodprocess_annotation
(self, annotation_database)
prj/cnvid_vtp/roi_univl/univl/pretrain_video_text/dataset.py:41
↓ 1 callersMethodprocess_annotation
(self, annotation_database)
antmmf/datasets/database/annotated.py:157
↓ 1 callersFunctionprocess_vision_info
( conversations: list[dict] | list[list[dict]], )
prj/M2_omni/models/m2omni_utils.py:405
↓ 1 callersMethodproject
(self, param_name, param_data, epsilon)
antmmf/models/nlp_adversarial.py:111
↓ 1 callersMethodprompt_wrap
(self, input_ids, image_embeds=None, video_embeds=None, audio_embeds=None, target_embeds=None)
prj/M2_omni/models/modeling_m2omni.py:760
↓ 1 callersMethodprompt_wrap_audio
(self, input_ids, inputs_embeds, audio_embeds, audio_token_id=None)
prj/M2_omni/models/modeling_m2omni.py:739
↓ 1 callersMethodprompt_wrap_image
(self, input_ids, inputs_embeds, vision_embeds, image_token_id=None)
prj/M2_omni/models/modeling_m2omni.py:695
↓ 1 callersMethodprompt_wrap_video
(self, input_ids, inputs_embeds, vision_embeds, video_token_id=None)
prj/M2_omni/models/modeling_m2omni.py:717
↓ 1 callersMethodprune_model
(self)
prj/snps3_vtp/roi_univl/univl/model/univl_base.py:56
↓ 1 callersMethodprune_model
(self)
prj/dmae_vtp/roi_univl/univl/model/univl_base.py:56
↓ 1 callersMethodprune_model
(self)
prj/base_vtp/roi_univl/univl/model/univl_base.py:56
↓ 1 callersMethodprune_model
(self)
prj/cnvid_vtp/roi_univl/univl/model/univl_base.py:56
↓ 1 callersFunctionrandom_affine
Random affine transformation, position, angle, scale
antmmf/utils/dataset_utils.py:162
↓ 1 callersFunctionrandom_black
Randomly fill black color to the four sides of the image at different scales
antmmf/utils/dataset_utils.py:101
↓ 1 callersFunctionrandom_blur
Add random blur types to one image. @params random_type: string in allowed_blur_types - 'gaussian'
antmmf/utils/dataset_utils.py:406
↓ 1 callersFunctionrandom_color
(img, **kwargs)
antmmf/utils/dataset_utils.py:201
↓ 1 callersFunctionrandom_crop
Randomly crop the four sides of the image at different scales
antmmf/utils/dataset_utils.py:54
↓ 1 callersFunctionrandom_flip
Randomly flip image around
antmmf/utils/dataset_utils.py:154
↓ 1 callersFunctionrandom_gray
Add random gray types to one image. @params random_type: string in allowed_gray_types - 'single': single_channle as output gray v
antmmf/utils/dataset_utils.py:493
↓ 1 callersFunctionrandom_noise
Add random noise types to one image. @params random_type: string in allowed_noise_types - 'gaussian' Gaussian-distributed addit
antmmf/utils/dataset_utils.py:316
↓ 1 callersMethodrandom_region
Implementation refer to: https://github.com/e-bug/volta/blob/9e5202141920600d58a9c5c17519ca453795d65d/volta/datasets/concept_cap_data
prj/snps3_vtp/roi_univl/roi/region_processor.py:43
↓ 1 callersMethodrandom_region
Implementation refer to: https://github.com/e-bug/volta/blob/9e5202141920600d58a9c5c17519ca453795d65d/volta/datasets/concept_cap_data
prj/dmae_vtp/roi_univl/roi/region_processor.py:43
↓ 1 callersMethodrandom_region
Implementation refer to: https://github.com/e-bug/volta/blob/9e5202141920600d58a9c5c17519ca453795d65d/volta/datasets/concept_cap_data
prj/base_vtp/roi_univl/roi/region_processor.py:43
↓ 1 callersMethodrandom_region
Implementation refer to: https://github.com/e-bug/volta/blob/9e5202141920600d58a9c5c17519ca453795d65d/volta/datasets/concept_cap_data
prj/cnvid_vtp/roi_univl/roi/region_processor.py:43
↓ 1 callersMethodrandom_reorder
random reorder frame positions copy from: https://github.com/linjieli222/HERO/blob/master/data/fom.py#L96
prj/snps3_vtp/roi_univl/univl/model/univl_video_pretrain.py:397
↓ 1 callersMethodrandom_reorder
random reorder frame positions copy from: https://github.com/linjieli222/HERO/blob/master/data/fom.py#L96
prj/dmae_vtp/roi_univl/univl/model/univl_video_pretrain.py:374
↓ 1 callersMethodrandom_reorder
random reorder frame positions copy from: https://github.com/linjieli222/HERO/blob/master/data/fom.py#L96
prj/base_vtp/roi_univl/univl/model/univl_video_pretrain.py:374
↓ 1 callersMethodrandom_reorder
random reorder frame positions copy from: https://github.com/linjieli222/HERO/blob/master/data/fom.py#L96
prj/cnvid_vtp/roi_univl/univl/model/univl_video_pretrain.py:380
↓ 1 callersMethodrandom_transform
(self, x)
antmmf/datasets/processors/image_processors.py:548
↓ 1 callersMethodread_bytes
(self, video_name)
antmmf/datasets/database/video_database.py:322
↓ 1 callersFunctionread_checksum
(filepath)
prj/cnvid_vtp/download_cnvid/download_cnvid_video.py:132
↓ 1 callersMethodread_frames_decord
( self, video_path, num_clips, fix_start=None, begin_time=None, end_time=None )
antmmf/utils/video_utils.py:77
↓ 1 callersMethodread_frames_from_img_dir
( self, video_path, num_frames, fix_start=None, frame_resample="uniform" )
antmmf/utils/video_utils.py:121
↓ 1 callersFunctionread_urls_csv
(filepath)
prj/cnvid_vtp/download_cnvid/download_cnvid_video.py:119
↓ 1 callersMethodrecord_all_to_all_stats
(self)
prj/M2_Encoder/vlmo/torchscale/component/xmoe/moe_layer.py:314
↓ 1 callersMethodrel_transform
(self, ent_embed, rel_embed)
antmmf/modules/graph.py:367
↓ 1 callersMethodrel_transform
(self, ent_embed, rel_embed)
antmmf/modules/graph.py:521
↓ 1 callersMethodrel_transform
(self, ent_embed, edge_type_embed)
antmmf/modules/message_passing/delta_conv.py:280
↓ 1 callersMethodremove_redundant_ckpts
(self)
antmmf/common/checkpoint.py:310
↓ 1 callersMethodreport
(self, train_flops, global_step=None)
antmmf/common/metrics_reporter.py:201
↓ 1 callersMethodrescale
(param, layer_id)
prj/M2_Encoder/vlmo/modules/vlmo_module.py:271
↓ 1 callersMethodreset
(self)
antmmf/modules/metrics/roc_auc.py:28
↓ 1 callersMethodreset
(self)
antmmf/modules/metrics/mce_accuracy.py:21
↓ 1 callersMethodreset
(self)
antmmf/modules/metrics/mce_accuracy.py:97
↓ 1 callersMethodreset
(self)
antmmf/modules/metrics/span_f1.py:25
↓ 1 callersMethodreset
(self)
antmmf/modules/metrics/multi_macro_f1.py:29
↓ 1 callersMethodreset
(self)
antmmf/modules/metrics/bleu4.py:25
↓ 1 callersMethodreset
(self)
antmmf/modules/metrics/recall_at_k.py:94
↓ 1 callersMethodreset
(self)
antmmf/modules/metrics/multi_accuracy.py:28
↓ 1 callersMethodreset
(self)
antmmf/modules/metrics/rouge_antmmf.py:25
↓ 1 callersMethodreset
(self)
antmmf/modules/metrics/ks.py:23
↓ 1 callersMethodreset
(self)
antmmf/common/meter.py:38
↓ 1 callersMethodreset_parameters
(self)
prj/M2_Encoder/vlmo/torchscale/component/embedding.py:87
↓ 1 callersMethodreset_parameters
(self)
antmmf/modules/graph.py:87
↓ 1 callersMethodreset_parameters
(self)
antmmf/modules/graph.py:146
↓ 1 callersMethodreset_parameters
(self)
antmmf/modules/graph.py:207
↓ 1 callersMethodreset_parameters
(self)
antmmf/modules/embeddings/detr_position_embedding_learned.py:26
↓ 1 callersMethodreset_parameters
(self)
antmmf/modules/layers/linear.py:63
↓ 1 callersMethodreset_parameters
(self)
antmmf/modules/layers/exu.py:24
↓ 1 callersMethodreset_parameters
Initialize the transition parameters. The parameters will be initialized randomly from a uniform distribution between -0.1 and 0.1.
antmmf/modules/layers/crf.py:50
↓ 1 callersMethodreset_profile
(self, global_step=None)
antmmf/common/metrics_reporter.py:163
↓ 1 callersMethodreset_weight_and_bias
(self)
antmmf/modules/layers/conditional_layer_norm.py:34
↓ 1 callersMethodresize_image_to_target
Args: img: opencv BGR image Returns: image with longer side matching target_size
antmmf/utils/image_ops.py:648
↓ 1 callersFunctionreturn_type_repr
(signature)
antmmf/utils/inspector.py:62
↓ 1 callersMethodrot_pos_emb
(self, grid_thw)
prj/M2_omni/models/qwen2_vit.py:318
↓ 1 callersFunctionrotate_every_two
(x)
prj/M2_Encoder/vlmo/torchscale/component/xpos_relative_position.py:15
↓ 1 callersFunctionrotate_level_to_args
(MAX_LEVEL, replace_value)
prj/M2_Encoder/vlmo/transforms/randaugment.py:257
↓ 1 callersFunctionround_repeats
Calculate module's repeat number of a block based on depth multiplier. Use depth_coefficient of global_params. Args: repeats (int)
antmmf/modules/vision/backbone/efficientnet.py:791
↓ 1 callersFunctionrun
()
prj/snps3_vtp/run.py:15
← previousnext →1,501–1,600 of 4,004, ranked by callers