MCPcopy Create free account

hub / github.com/PKU-ICST-MIPL/FineSports_CVPR2024 / functions

Functions799 in github.com/PKU-ICST-MIPL/FineSports_CVPR2024

⨍ Functions 799◇ Types & classes 157↳ Endpoints 1
↓ 1 callersFunctionbuild_I3D
(cfg)
models/backbone_builder.py:121
↓ 1 callersFunctionbuild_backbone
(cfg)
models/backbone_builder.py:115
↓ 1 callersFunctionbuild_dataloader
(cfg)
datasets/basketball_jhmdb_frame.py:279
↓ 1 callersFunctionbuild_log_dir
(cfg)
utils/utils.py:28
↓ 1 callersFunctionbuild_matcher
(cfg)
models/detr/matcher_ucf.py:94
↓ 1 callersFunctionbuild_model
(cfg)
models/postal_basketball.py:240
↓ 1 callersFunctionbuild_model
(n_classes=400, sample_size=224, sample_duration=128, pretrain
models/backbones/ir_CSN_152.py:185
↓ 1 callersFunctionbuild_model
(n_classes=400, sample_size=224, sample_duration=128, pretrain
models/backbones/ir_CSN_50.py:185
↓ 1 callersFunctionbuild_scheduler
(cfg, optimizer, n_iter_per_epoch)
utils/lr_scheduler.py:13
↓ 1 callersFunctionbuild_swin
(cfg)
models/backbones/video_swin_transformer.py:595
↓ 1 callersMethodclear
(self)
evaluates/evaluate_ava.py:54
↓ 1 callersMethodclear
Clears the state to prepare for a fresh evaluation.
evaluates/utils/object_detection_evaluation.py:99
↓ 1 callersMethodclone_layers
(self, layers_to_clone)
models/transformer/transformer.py:49
↓ 1 callersFunctioncompute_mask
(D, H, W, window_size, shift_size, device)
models/backbones/video_swin_transformer.py:331
↓ 1 callersMethodcompute_object_detection_metrics
Evaluates detections as being tp, fp or ignored from a single image. The evaluation is done in two stages: 1. All detections are matched to
evaluates/utils/per_image_evaluation.py:45
↓ 1 callersFunctionconcatenate
Concatenate list of BoxLists. This op concatenates a list of input BoxLists into a larger BoxList. It also handles concatenation of BoxList fiel
evaluates/utils/np_box_list_ops.py:424
↓ 1 callersFunctionconvert_label_map_to_categories
Loads label map proto and returns categories list compatible with eval. This function loads a label map and returns a list of dicts, each of which
evaluates/utils/label_map_util.py:73
↓ 1 callersMethodcopy_params
(self)
models/BLIP/models/blip_retrieval.py:229
↓ 1 callersMethodcopy_params
(self)
models/BLIP/models/blip_pretrain.py:217
↓ 1 callersFunctioncreate_category_index
Creates dictionary of COCO compatible categories keyed by category id. Args: categories: a list of dicts, each of which has the following keys:
evaluates/utils/label_map_util.py:37
↓ 1 callersFunctiondeploy_model
Deploy model to multiple GPUs for DDP training.
utils/model_utils.py:44
↓ 1 callersMethodevaluate
Evaluates detections and returns a dictionary of metrics.
evaluates/utils/object_detection_evaluation.py:94
↓ 1 callersFunctionevaluation
(model, data_loader, device, config)
models/BLIP/train_vqa.py:63
↓ 1 callersFunctionevaluation
(model, data_loader, tokenizer, device, config)
models/BLIP/eval_retrieval_video.py:31
↓ 1 callersMethodforward_part1
(self, x, mask_matrix)
models/backbones/video_swin_transformer.py:232
↓ 1 callersMethodforward_part2
(self, x)
models/backbones/video_swin_transformer.py:268
↓ 1 callersMethodforward_post
(self, src, orig_shape, src_mask: Optional[Tens
models/transformer/transformer_layers.py:70
↓ 1 callersMethodforward_post
(self, src, src_mask: Optional[Tensor] = None,
models/transformer/transformer.py:171
↓ 1 callersMethodforward_post
(self, num_feat, tgt, memory, tgt_mask: Optional[Tensor] = None, mem
models/transformer/transformer.py:236
↓ 1 callersMethodforward_pre
(self, src, src_mask: Optional[Tensor] = None, src_key_padding_mask: O
models/transformer/transformer_layers.py:98
↓ 1 callersMethodforward_pre
(self, src, src_mask: Optional[Tensor] = None, src_key_padding_mask: O
models/transformer/transformer.py:188
↓ 1 callersMethodforward_pre
(self, num_feat, tgt, memory, tgt_mask: Optional[Tensor] = None, memor
models/transformer/transformer.py:269
↓ 1 callersFunctionget_bn_params
(sess, name)
models/I3D_Backbone.py:335
↓ 1 callersFunctionget_conv_params
(sess, name, bias=False)
models/I3D_Backbone.py:306
↓ 1 callersMethodget_coordinates
Get corner coordinates of boxes. Returns: a list of 4 1-d numpy arrays [y_min, x_min, y_max, x_max]
evaluates/utils/np_box_list.py:106
↓ 1 callersMethodget_extended_attention_mask
Makes broadcastable attention and causal masks so that future and masked tokens are ignored. Arguments: attention_mask (
models/BLIP/models/nlvr_encoder.py:644
↓ 1 callersMethodget_extended_attention_mask
Makes broadcastable attention and causal masks so that future and masked tokens are ignored. Arguments: attention_mask (
models/BLIP/models/med.py:609
↓ 1 callersFunctionget_local_ip_and_match
(ip_list)
pipelines/launch.py:8
↓ 1 callersMethodget_random_ops
(self)
models/BLIP/transform/randaugment.py:321
↓ 1 callersFunctionget_rank
()
utils/misc.py:418
↓ 1 callersFunctionget_rank
()
models/transformer/util/misc.py:384
↓ 1 callersFunctionget_rank
()
models/BLIP/utils.py:239
↓ 1 callersFunctionget_rank
()
models/detr/util/misc.py:384
↓ 1 callersFunctionget_size
(image_size, size, max_size=None)
datasets/video_transforms.py:108
↓ 1 callersFunctionget_size_with_aspect_ratio
(image_size, size, max_size=None)
datasets/video_transforms.py:88
↓ 1 callersMethodget_text_embeddings
(self, text, label, stage, color_pred=None, number_pred=None)
models/BLIP/prompt_learner.py:209
↓ 1 callersFunctioninterpolate
Equivalent to nn.functional.interpolate, but with support for empty batch sizes. This will eventually be supported natively by PyTorch, and t
utils/misc.py:502
↓ 1 callersFunctionioa
Computes pairwise intersection-over-area between box and mask collections. Intersection-over-area (ioa) between two masks mask1 and mask2 is define
evaluates/utils/np_box_mask_list_ops.py:93
↓ 1 callersFunctionioa
Computes pairwise intersection-over-area between box collections. Intersection-over-area (ioa) between two boxes box1 and box2 is defined as thei
evaluates/utils/np_box_list_ops.py:78
↓ 1 callersFunctionis_main_process
()
utils/misc.py:424
↓ 1 callersFunctionis_main_process
()
models/transformer/util/misc.py:390
↓ 1 callersFunctionis_main_process
()
models/BLIP/utils.py:245
↓ 1 callersFunctionis_main_process
()
models/detr/util/misc.py:390
↓ 1 callersFunctionitm_eval
(scores_v2t, scores_t2v, txt2vmg, vid2txt)
models/BLIP/eval_retrieval_video.py:138
↓ 1 callersFunctionlayer_norm
(d_model, condition=True)
models/transformer/transformer_layers.py:18
↓ 1 callersMethodload_GT_from_path
(self, file_lst)
evaluates/evaluate_ava.py:58
↓ 1 callersMethodload_annotation
(self, sample_id, start, index, p_t)
datasets/basketball_jhmdb_frame.py:128
↓ 1 callersFunctionload_checkpoint
(model,url_or_filename)
models/BLIP/models/blip_nlvr.py:76
↓ 1 callersMethodload_detection_from_path
(self, file_lst)
evaluates/evaluate_ava.py:101
↓ 1 callersFunctionload_detr_weights
(model, pretrain_dir, cfg)
utils/model_utils.py:10
↓ 1 callersFunctionload_detr_weights
(model, pretrain_dir, cfg)
models/postal_basketball.py:205
↓ 1 callersFunctionload_image
(image, image_size, device)
models/BLIP/predict.py:87
↓ 1 callersFunctionload_jsonl
(filename)
models/BLIP/data/video_dataset.py:29
↓ 1 callersFunctionload_model
Load pretrained model weights.
utils/model_utils.py:75
↓ 1 callersMethodload_pretrain
(self, I3D_ckpt_path)
models/I3D_Backbone.py:425
↓ 1 callersFunctionload_weights
(model, pretrain_path, load_fc=True, use_affine=False, tune_point=5)
models/backbones/ir_CSN_152.py:238
↓ 1 callersMethodloadvideo
(self, mid_point, sample_id, target, p_t)
datasets/basketball_jhmdb_frame.py:188
↓ 1 callersFunctionmain
(args, config)
models/BLIP/train_vqa.py:97
↓ 1 callersFunctionmain
(args, config)
models/BLIP/train_retrieval.py:218
↓ 1 callersFunctionmain
(args, config)
models/BLIP/train_nlvr.py:94
↓ 1 callersFunctionmain
(args, config)
models/BLIP/eval_nocaps.py:53
↓ 1 callersFunctionmain
(args, config)
models/BLIP/eval_retrieval_video.py:184
↓ 1 callersFunctionmain
(args, config)
models/BLIP/train_caption.py:82
↓ 1 callersFunctionmain_worker
The main_worker process function (on individual GPU)
pipelines/launch.py:37
↓ 1 callersMethodmedian
(self)
models/BLIP/utils.py:62
↓ 1 callersFunctionnested_tensor_from_tensor_list
(tensor_list: List[Tensor])
models/transformer/util/misc.py:294
↓ 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
evaluates/utils/np_box_mask_list_ops.py:161
↓ 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
evaluates/utils/np_box_list_ops.py:161
↓ 1 callersFunctionpad
(images, target, padding)
datasets/video_transforms.py:148
↓ 1 callersFunctionparse_id
(class_num)
evaluates/evaluate_ucf.py:14
↓ 1 callersFunctionposterize_level_to_args
(MAX_LEVEL)
models/BLIP/transform/randaugment.py:251
↓ 1 callersMethodprune_heads
(self, heads)
models/BLIP/models/nlvr_encoder.py:262
↓ 1 callersMethodprune_heads
(self, heads)
models/BLIP/models/med.py:249
↓ 1 callersMethodrank_answer
(self, question_states, question_atts, answer_ids, answer_atts, k)
models/BLIP/models/blip_vqa.py:120
↓ 1 callersMethodreload_laion
(self, epoch)
models/BLIP/data/pretrain_dataset.py:39
↓ 1 callersMethodreset
(self)
utils/utils.py:63
↓ 1 callersFunctionresize
(images, target, size, max_size=None)
datasets/video_transforms.py:85
↓ 1 callersFunctionrotate_level_to_args
(MAX_LEVEL, replace_value)
models/BLIP/transform/randaugment.py:258
↓ 1 callersMethodsave_attention_map
(self, attention_map)
models/BLIP/models/vit.py:64
↓ 1 callersMethodsave_attention_map
(self, attention_map)
models/BLIP/models/nlvr_encoder.py:122
↓ 1 callersMethodsave_attention_map
(self, attention_map)
models/BLIP/models/med.py:132
↓ 1 callersFunctionsave_checkpoint
(cfg, epoch, model, max_accuracy, optimizer, lr_scheduler, filename, model_ema=None)
utils/model_utils.py:128
↓ 1 callersFunctionsave_model
Save trained model weights.
utils/model_utils.py:113
↓ 1 callersFunctionscale
Scale box coordinates in x and y dimensions. Args: boxlist: BoxList holding N boxes y_scale: float x_scale: float Returns: boxli
evaluates/utils/np_box_list_ops.py:308
↓ 1 callersFunctionsetup_for_distributed
This function disables printing when not in master process
utils/misc.py:389
↓ 1 callersFunctionsetup_for_distributed
This function disables printing when not in master process
models/transformer/util/misc.py:355
↓ 1 callersFunctionsetup_for_distributed
This function disables printing when not in master process
models/BLIP/utils.py:210
↓ 1 callersFunctionsetup_for_distributed
This function disables printing when not in master process
models/detr/util/misc.py:355
↓ 1 callersFunctionsimplify_padding
(padding_shapes)
models/I3D_Backbone.py:30
↓ 1 callersFunctionsolarize_level_to_args
(MAX_LEVEL)
models/BLIP/transform/randaugment.py:240
← previousnext →201–300 of 799, ranked by callers