MCPcopy Create free account

hub / github.com/ChenhongyiYang/QueryDet-PyTorch / functions

Functions164 in github.com/ChenhongyiYang/QueryDet-PyTorch

↓ 1 callersMethodtrain_forward
(self, batched_inputs, just_forward=False)
models/querydet/detector.py:169
↓ 1 callersMethodvisualize_training
(self, batched_inputs, results)
models/retinanet/retinanet.py:141
↓ 1 callersFunctionvoc_ap
(rec, prec)
visdrone_eval/viseval/calc_accuracy.py:67
Method__call__
(self, boxes, scores, class_idxs)
utils/soft_nms.py:146
Method__call__
(self, gt_boxes, anchors)
utils/loop_matcher.py:36
Method__call__
Args: dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format. Returns: dict: a format that
utils/val_mapper_with_ann.py:29
Method__call__
(self, dataset_dict)
visdrone/mapper.py:50
Method__init__
(self, distributed, unit, out_file=None)
utils/time_evaluator.py:10
Method__init__
(self, method, gaussian_sigma, linear_threshold, prune_threshold)
utils/soft_nms.py:140
Method__init__
( self, thresholds: List[float], labels: List[int], allow_low_quality_matches: bool = False )
utils/loop_matcher.py:7
Method__init__
(self, out_json, distributed=True, class_add_1=True)
utils/json_evaluator.py:18
Method__init__
(self, *args, stats_mode="", **kwargs)
utils/merged_sync_bn.py:55
Method__init__
(self, cfg)
utils/val_mapper_with_ann.py:19
Method__init__
Args: cfg (CfgNode):
train_tools/visdrone_train.py:64
Method__init__
Args: cfg (CfgNode):
train_tools/coco_train.py:60
Method__init__
(self, gt_json, det_json, out_dir)
visdrone/json_to_txt.py:11
Method__init__
(self, cfg, is_train=True)
visdrone/mapper.py:36
Method__init__
(self, cfg)
models/querydet/detector.py:73
Method__init__
(self, cfg, in_channels, conv_channels, num_convs, num_anchors)
models/querydet/det_head.py:28
Method__init__
(self, cfg, in_channels, conv_channels, num_convs, num_anchors)
models/querydet/det_head.py:133
Method__init__
(self, in_channels, conv_channels, num_convs, pred_channels, pred_prior=None)
models/querydet/det_head.py:267
Method__init__
(self, anchor_num, num_classes, score_th=0.12, context=2)
models/querydet/qinfer.py:25
Method__init__
(self, cfg, input_shape: List[ShapeSpec])
models/retinanet/retinanet.py:438
Methodbackward
(ctx, *args)
utils/gradient_checkpoint.py:79
Methodbackward
(ctx, grad_output)
utils/merged_sync_bn.py:23
Functionbatched_soft_nms_rotated
Performs soft non-maximum suppression in a batched fashion on rotated bounding boxes. Each index value correspond to a category, and NMS
utils/soft_nms.py:150
Methodbuild_evaluator
(cls, cfg, dataset_name, output_folder=None)
train_tools/coco_infer.py:58
Methodbuild_evaluator
(cls, cfg, dataset_name, output_folder=None)
train_tools/coco_train.py:105
Methodbuild_test_loader
(cls, cfg, dataset_name)
train_tools/coco_train.py:114
Functioncheckpoint_sequential
r"""A helper function for checkpointing sequential models. Sequential models execute a list of modules/functions in order (sequentially). The
utils/gradient_checkpoint.py:167
Methodconvert_gt_cls
(logits, gt_class, f_idxs)
models/querydet/detector.py:275
Methodconvert_gt_cls
(logits, gt_class, f_idxs)
models/retinanet/retinanet.py:274
Methoddevice
(self)
models/querydet/detector.py:160
Methodevaluate
(self)
utils/time_evaluator.py:28
Methodevaluate
(self)
utils/json_evaluator.py:45
Functionforward
(input)
utils/gradient_checkpoint.py:213
Methodforward
(self, features)
utils/anchor_gen.py:25
Methodforward
(ctx, run_function, preserve_rng_state, *args)
utils/gradient_checkpoint.py:58
Methodforward
(ctx, input)
utils/merged_sync_bn.py:15
Methodforward
(self, inputs)
utils/merged_sync_bn.py:71
Methodforward
(self, batched_inputs, just_forward=False)
models/querydet/detector.py:163
Methodforward
(self, features)
models/querydet/det_head.py:66
Methodforward
(self, features)
models/querydet/det_head.py:115
Methodforward
(self, features, lvl_start)
models/querydet/det_head.py:180
Methodforward
(self, features)
models/querydet/det_head.py:298
Methodforward
(self, batched_inputs)
models/retinanet/retinanet.py:171
Methodforward
Arguments: features (list[Tensor]): FPN feature map tensors in high to low resolution. Each tensor in the list co
models/retinanet/retinanet.py:483
Methodget_params
(self)
models/querydet/det_head.py:82
Methodget_params
(self)
models/querydet/det_head.py:253
Methodget_params
(self)
models/querydet/det_head.py:338
Functionpermute_all_cls_and_box_to_N_HWA_K_and_concat
(box_cls, box_delta, num_classes=80)
models/querydet/detector.py:54
Functionpermute_all_cls_and_box_to_N_HWA_K_and_concat
Rearrange the tensor layout from the network output, i.e.: list[Tensor]: #lvl tensors of shape (N, A x K, Hi, Wi) to per-image prediction
models/retinanet/retinanet.py:44
Functionpermute_to_N_HWA_K
(tensor, K)
models/querydet/qinfer.py:7
Methodprocess
Args: inputs: the inputs to a COCO model (e.g., GeneralizedRCNN). It is a list of dict. Each dict corresponds to
utils/coco_eval_fpn.py:64
Methodprocess
(self, inputs, outputs)
utils/time_evaluator.py:22
Methodprocess
(self, inputs, outputs)
utils/json_evaluator.py:34
Functionread_all_labels
(ann_root)
visdrone/utils.py:27
Functionrun_conv2d
(x, weights, bias)
models/querydet/qinfer.py:15
Functionstart_train
(args)
train_tools/visdrone_infer.py:162
Functionstart_train
(args)
train_tools/visdrone_train.py:236
Functionstart_train
(args)
train_tools/coco_infer.py:139
Functionstart_train
(args)
train_tools/coco_train.py:189
Functiontrivial_batch_collator
(batch)
visdrone/dataloader.py:151
Functionworker_init_reset_seed
(worker_id)
visdrone/dataloader.py:147
← previous101–164 of 164, ranked by callers