MCPcopy Create free account

hub / github.com/OpenGVLab/unmasked_teacher / functions

Functions1,198 in github.com/OpenGVLab/unmasked_teacher

↓ 1 callersFunctionget_position_angle_vec
(position)
single_modality/models/modeling_pretrain_umt.py:23
↓ 1 callersFunctionget_pyav_video_duration
(video_reader)
multi_modality/dataset/video_utils.py:34
↓ 1 callersFunctionget_rank
()
single_modality/utils.py:296
↓ 1 callersFunctionget_rank
()
single_modality/action_detection/utils.py:234
↓ 1 callersFunctionget_sim_for_each_question
TODO: Docstring for get_sim_for_each_question. Args: model (TODO): TODO pooled_image_feat (torch.Tensor): Shape: [b,t, c]
multi_modality/tasks/retrieval_mc.py:32
↓ 1 callersFunctionget_sinusoid_encoding_table
Sinusoid position encoding table
single_modality/action_detection/modeling_finetune.py:160
↓ 1 callersMethodget_size
(self, image_size)
single_modality/action_detection/alphaction/dataset/transforms/video_transforms.py:60
↓ 1 callersFunctionget_slow_model_cfg
(cfg)
single_modality/action_detection/alphaction/modeling/backbone/slowfast.py:10
↓ 1 callersMethodget_video_info
(self, index)
single_modality/action_detection/data/ava.py:124
↓ 1 callersFunctionget_world_size
()
single_modality/utils.py:290
↓ 1 callersFunctionget_world_size
()
single_modality/action_detection/utils.py:228
↓ 1 callersMethodhas_checkpoint
(self)
single_modality/action_detection/alphaction/utils/checkpoint.py:85
↓ 1 callersMethodhas_field
(self, field)
single_modality/action_detection/alphaction/structures/bounding_box.py:45
↓ 1 callersFunctionhas_memory
(ia_config)
single_modality/action_detection/alphaction/utils/IA_helper.py:18
↓ 1 callersFunctionhas_person
(ia_config)
single_modality/action_detection/alphaction/utils/IA_helper.py:8
↓ 1 callersFunctioninference
( model, data_loader, dataset_name, mem_active=False, output_folder=No
single_modality/action_detection/alphaction/engine/inference.py:156
↓ 1 callersFunctioninflate_weight
(weight_2d, time_dim, center=True)
multi_modality/models/backbones/vit/clip.py:159
↓ 1 callersFunctioninflate_weight
(weight_2d, time_dim, center=True)
single_modality/models/clip.py:175
↓ 1 callersFunctioninit_distributed_mode
(args)
multi_modality/utils/distributed.py:63
↓ 1 callersMethodinit_entry
(self)
multi_modality/tasks/vqa_utils.py:129
↓ 1 callersFunctioninterpolate_pos_embed_online
( pos_embed, orig_size: Tuple[int], new_size: Tuple[int], num_extra_tokens: int )
single_modality/action_detection/modeling_finetune.py:362
↓ 1 callersFunctioninterpolate_temporal_pos_embed
temp_embed_old: (1, num_frames_old, 1, d) Returns: temp_embed_new: (1, num_frames_new, 1, d)
multi_modality/models/utils.py:56
↓ 1 callersFunctionioa
Computes pairwise intersection-over-area between box and mask collections. Intersection-over-area (ioa) between two masks mask1 and mask2 is define
single_modality/action_detection/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_mask_list_ops.py:91
↓ 1 callersFunctionioa
Computes pairwise intersection-over-area between box collections. Intersection-over-area (ioa) between two boxes box1 and box2 is defined as thei
single_modality/action_detection/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_list_ops.py:77
↓ 1 callersFunctionis_main_process
()
single_modality/utils.py:302
↓ 1 callersFunctionis_main_process
()
single_modality/action_detection/utils.py:240
↓ 1 callersFunctionis_port_in_use
(port)
multi_modality/utils/distributed.py:57
↓ 1 callersFunctionitm_eval
(scores_i2t, scores_t2i, txt2img, img2txt)
multi_modality/tasks/retrieval_utils.py:400
↓ 1 callersFunctionload
(module, prefix='')
single_modality/utils.py:364
↓ 1 callersFunctionload
(module, prefix='')
single_modality/action_detection/utils.py:302
↓ 1 callersMethodload_and_transform_media_data_image
(self, index, data_path)
multi_modality/dataset/base_dataset.py:64
↓ 1 callersMethodload_and_transform_media_data_video
(self, index, data_path)
multi_modality/dataset/base_dataset.py:69
↓ 1 callersMethodload_box_file
(self, box_file, score_thresh=0.0)
single_modality/action_detection/data/ava.py:133
↓ 1 callersFunctionload_c2_format
(f, weight_map)
single_modality/action_detection/alphaction/utils/c2_model_loading.py:37
↓ 1 callersFunctionload_image_from_path
(image_path, client)
multi_modality/dataset/utils.py:19
↓ 1 callersFunctionload_state_dict
(model, loaded_state_dict, no_head)
single_modality/action_detection/alphaction/utils/model_serialization.py:74
↓ 1 callersFunctionload_vocab
Loads a vocabulary file into a dictionary.
multi_modality/models/backbones/bert/tokenization_bert.py:97
↓ 1 callersFunctionmain
(config)
multi_modality/tasks/pretrain.py:155
↓ 1 callersFunctionmain
(args)
single_modality/run_umt_pretraining.py:180
↓ 1 callersFunctionmain
(args)
single_modality/run_mae_pretraining.py:149
↓ 1 callersFunctionmain
(args, ds_init)
single_modality/run_class_finetuning.py:222
↓ 1 callersFunctionmain
(args, ds_init)
single_modality/action_detection/run_class_finetuning.py:166
↓ 1 callersFunctionmake_batch_data_sampler
( dataset, sampler, aspect_grouping, videos_per_batch, num_iters=None, start_iter=0, drop_last=False )
single_modality/action_detection/alphaction/dataset/build.py:95
↓ 1 callersFunctionmake_data_sampler
(dataset, shuffle, distributed)
single_modality/action_detection/alphaction/dataset/build.py:69
↓ 1 callersFunctionmake_ia_structure
(cfg, dim_in)
single_modality/action_detection/alphaction/modeling/roi_heads/action_head/IA_structure.py:405
↓ 1 callersFunctionmake_roi_action_accuracy_evaluator
(cfg)
single_modality/action_detection/alphaction/modeling/roi_heads/action_head/metric.py:61
↓ 1 callersFunctionmake_roi_action_feature_extractor
(cfg, dim_in)
single_modality/action_detection/alphaction/modeling/roi_heads/action_head/roi_action_feature_extractor.py:185
↓ 1 callersFunctionmake_roi_action_loss_evaluator
(cfg)
single_modality/action_detection/alphaction/modeling/roi_heads/action_head/loss.py:80
↓ 1 callersFunctionmake_roi_action_post_processor
(cfg)
single_modality/action_detection/alphaction/modeling/roi_heads/action_head/inference.py:42
↓ 1 callersFunctionmake_roi_action_predictor
(cfg, dim_in)
single_modality/action_detection/alphaction/modeling/roi_heads/action_head/roi_action_predictors.py:34
↓ 1 callersMethodmask
( self, input_ids, vocab_size, device, targets=None, masked_in
multi_modality/models/criterions.py:275
↓ 1 callersMethodmax
(self)
single_modality/utils.py:67
↓ 1 callersMethodmax_pooling_zero_safe
(self, x)
single_modality/action_detection/alphaction/modeling/roi_heads/action_head/roi_action_feature_extractor.py:65
↓ 1 callersMethodmerge_list
merge commandline opts. Args: cfg: (dict): The config to be merged. opts (list): The list to merge. Format: [key1, na
multi_modality/utils/config.py:172
↓ 1 callersMethodmlm_loss
( self, text_encoder, text, vision_embeds, vision_atts, )
multi_modality/models/criterions.py:213
↓ 1 callersMethodno_weight_decay
(self)
multi_modality/models/backbones/vit/vit.py:384
↓ 1 callersFunctionnon_max_suppression
Non maximum suppression. This op greedily selects a subset of detection bounding boxes, pruning away boxes that have high IOU (intersection over
single_modality/action_detection/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_mask_list_ops.py:159
↓ 1 callersFunctionnon_max_suppression
Non maximum suppression. This op greedily selects a subset of detection bounding boxes, pruning away boxes that have high IOU (intersection over
single_modality/action_detection/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_list_ops.py:160
↓ 1 callersMethodprepare_boxlist
(self, boxes, scores, image_shape)
single_modality/action_detection/engine_for_finetuning.py:164
↓ 1 callersMethodprepare_boxlist
(self, boxes, scores, image_shape)
single_modality/action_detection/alphaction/modeling/roi_heads/action_head/inference.py:36
↓ 1 callersFunctionprepare_for_ava_detection
(predictions, dataset)
single_modality/action_detection/data/ava_eval.py:45
↓ 1 callersFunctionprepare_for_ava_detection
(predictions, dataset)
single_modality/action_detection/alphaction/dataset/datasets/evaluation/ava/ava_eval.py:42
↓ 1 callersMethodprepare_gt_data
(self, gt_data_or_path)
multi_modality/tasks/vqa_utils.py:118
↓ 1 callersFunctionpretrain_umt_base_patch16_224
(pretrained=False, **kwargs)
single_modality/models/modeling_pretrain_umt.py:273
↓ 1 callersMethodpretty_text
format dict to a string Args: cfg (EasyDict): the params. Returns: The string to display.
multi_modality/utils/config.py:33
↓ 1 callersMethodprocessDigitArticle
(self, inText)
multi_modality/tasks/vqa_utils.py:200
↓ 1 callersMethodprune_heads
(self, heads)
multi_modality/models/backbones/bert/xbert.py:524
↓ 1 callersFunctionpts_to_secs
Converts a present time with the given time base and start_pts offset to seconds. Returns: time_in_seconds (float): The correspondin
multi_modality/dataset/video_utils.py:19
↓ 1 callersFunctionrand_augment_ops
(magnitude=10, hparams=None, transforms=None)
single_modality/datasets/rand_augment.py:453
↓ 1 callersFunctionrand_bbox
Standard CutMix bounding-box Generates a random square bbox based on lambda value. This impl includes support for enforcing a border margin a
single_modality/datasets/mixup.py:30
↓ 1 callersFunctionrand_bbox_minmax
Min-Max CutMix bounding-box Inspired by Darknet cutmix impl, generates a random rectangular bbox based on min/max percent values applied to e
single_modality/datasets/mixup.py:54
↓ 1 callersMethodrank_answer
question_states: (bsz, Lq, d) answer_ids: answer input id after tokenization, (#answers, La)
multi_modality/models/umt_qa.py:136
↓ 1 callersFunctionread_exclusions
Reads a CSV file of excluded timestamps. Args: exclusions_file: Path of file containing a csv of video-id,timestamp. Returns: A
single_modality/action_detection/data/ava_eval.py:84
↓ 1 callersFunctionread_exclusions
Reads a CSV file of excluded timestamps. Args: exclusions_file: Path of file containing a csv of video-id,timestamp. Returns: A
single_modality/action_detection/alphaction/dataset/datasets/evaluation/ava/ava_eval.py:81
↓ 1 callersFunctionread_labelmap
Reads a labelmap without the dependency on protocol buffers. Args: labelmap_file: Path of file containing a label map protocol buffer.
single_modality/action_detection/data/ava_eval.py:104
↓ 1 callersFunctionread_labelmap
Reads a labelmap without the dependency on protocol buffers. Args: labelmap_file: Path of file containing a label map protocol buffer.
single_modality/action_detection/alphaction/dataset/datasets/evaluation/ava/ava_eval.py:101
↓ 1 callersMethodreset_parameters
(self)
single_modality/action_detection/alphaction/layers/batch_norm.py:31
↓ 1 callersMethodreset_running_stats
(self)
single_modality/action_detection/alphaction/layers/batch_norm.py:26
↓ 1 callersMethodreturn_null_box
(self, im_w, im_h)
single_modality/action_detection/alphaction/dataset/datasets/ava.py:198
↓ 1 callersMethodsample_box
(self, boxes)
single_modality/action_detection/modeling_finetune.py:309
↓ 1 callersMethodsample_box
(self, boxes)
single_modality/action_detection/alphaction/modeling/roi_heads/action_head/loss.py:24
↓ 1 callersFunctionsaturation_jitter
Perfrom saturation jittering on the input images. The channels of images should be in order BGR. Args: var (float): jitter ratio
single_modality/datasets/video_transforms.py:387
↓ 1 callersMethodsave_attention_map
(self, attention_map)
multi_modality/models/backbones/bert/xbert.py:379
↓ 1 callersFunctionsave_on_master
(*args, **kwargs)
single_modality/action_detection/utils.py:244
↓ 1 callersFunctionscale
Scale box coordinates in x and y dimensions. Args: boxlist: BoxList holding N boxes y_scale: float x_scale: float Returns: boxli
single_modality/action_detection/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_list_ops.py:307
↓ 1 callersFunctionseparate_batch_per_person
:param things: [b, max_others, c, t, h, w] :return [n, max_others, c, t, h, w]
single_modality/action_detection/alphaction/modeling/roi_heads/action_head/IA_structure.py:368
↓ 1 callersMethodsetAccuracy
(self, accQA, accQuesType, accAnsType)
multi_modality/tasks/vqa_utils.py:215
↓ 1 callersMethodsetEvalAnsType
(self, quesId, ansType, acc)
multi_modality/tasks/vqa_utils.py:234
↓ 1 callersMethodsetEvalQA
(self, quesId, acc)
multi_modality/tasks/vqa_utils.py:226
↓ 1 callersMethodsetEvalQuesType
(self, quesId, quesType, acc)
multi_modality/tasks/vqa_utils.py:229
↓ 1 callersFunctionsetup_config
Conbine yaml config and command line config with OmegaConf. Also converts types, e.g., `'None'` (str) --> `None` (None)
multi_modality/utils/config_utils.py:13
↓ 1 callersFunctionsetup_dataloaders
(config, dataset_name="vqa")
multi_modality/tasks/vqa.py:151
↓ 1 callersFunctionsetup_evaluate_config
setup evaluation default settings, e.g., disable wandb
multi_modality/utils/config_utils.py:23
↓ 1 callersFunctionsetup_for_distributed
(is_master)
multi_modality/utils/distributed.py:10
↓ 1 callersFunctionsetup_for_distributed
This function disables printing when not in master process
single_modality/utils.py:267
↓ 1 callersFunctionsetup_for_distributed
This function disables printing when not in master process
single_modality/action_detection/utils.py:205
↓ 1 callersFunctionsetup_logger
Initialize the MMF logger and set its verbosity level to "INFO". Outside libraries shouldn't call this in case they have set there own lo
multi_modality/utils/logger.py:67
↓ 1 callersFunctionsetup_output_dir
ensure not overwritting an exisiting/non-empty output dir
multi_modality/utils/config_utils.py:32
↓ 1 callersFunctionsetup_output_folder
Sets up and returns the output file where the logs will be placed based on the configuration passed. Usually "save_dir/logs/log_<timestamp>.txt".
multi_modality/utils/logger.py:40
↓ 1 callersFunctionsigmoid_focal_loss
(logits, targets, gamma, alpha, reduction='mean')
single_modality/action_detection/alphaction/layers/sigmoid_focal_loss.py:33
← previousnext →401–500 of 1,198, ranked by callers