Functions — github.com/SJTU-LuHe/TransVOD

hub / github.com/SJTU-LuHe/TransVOD / functions

Functions415 in github.com/SJTU-LuHe/TransVOD

⨍ Functions 415◇ Types & classes 92

↓ 1 callersFunctionbuild_position_encoding

(args)

models/position_encoding.py:87

↓ 1 callersMethodcache_images

(self)

datasets/torchvision_datasets/coco.py:46

↓ 1 callersFunctioncheck_forward_equal_with_pytorch_double

()

models/ops/test.py:32

↓ 1 callersFunctioncheck_forward_equal_with_pytorch_float

()

models/ops/test.py:48

↓ 1 callersFunctioncheck_gradient_numerical

(channels=4, grad_value=True, grad_sampling_loc=True, grad_attn_weight=True)

models/ops/test.py:63

↓ 1 callersFunctionconvert_coco_poly_to_mask

(segmentations, height, width)

datasets/vid_single.py:61

↓ 1 callersFunctionconvert_coco_poly_to_mask

(segmentations, height, width)

datasets/vid_multi.py:128

↓ 1 callersFunctionconvert_coco_poly_to_mask

(segmentations, height, width)

datasets/coco.py:43

↓ 1 callersMethodconvert_img_to_vid

Convert image data to video data.

datasets/coco_video_parser.py:20

↓ 1 callersMethodconvert_img_to_vid

Convert image data to video data.

datasets/parsers/coco_video_parser.py:22

↓ 1 callersFunctioncreate_common_coco_eval

(coco_eval, img_ids, eval_imgs)

datasets/coco_eval.py:200

↓ 1 callersFunctionevaluate

(model, criterion, postprocessors, data_loader, base_ds, device, output_dir)

engine_multi.py:79

↓ 1 callersFunctionevaluate

Run per image evaluation on given images and store results (a list of dict) in self.evalImgs :return: None

datasets/coco_eval.py:216

↓ 1 callersMethodforward_ffn

(self, tgt)

models/deformable_transformer_multi.py:298

↓ 1 callersMethodforward_ffn

(self, tgt)

models/deformable_transformer_multi.py:364

↓ 1 callersMethodforward_ffn

(self, src)

models/deformable_transformer_multi.py:412

↓ 1 callersMethodforward_ffn

(self, tgt)

models/deformable_transformer_multi.py:489

↓ 1 callersMethodforward_ffn

(self, src)

models/deformable_transformer_single.py:214

↓ 1 callersMethodforward_ffn

(self, tgt)

models/deformable_transformer_single.py:290

↓ 1 callersMethodforward_ffn

(self, tgt)

models/deformable_transformer_single.py:343

↓ 1 callersMethodgen_encoder_output_proposals

(self, memory, memory_padding_mask, spatial_shapes)

models/deformable_transformer_multi.py:100

↓ 1 callersMethodgen_encoder_output_proposals

(self, memory, memory_padding_mask, spatial_shapes)

models/deformable_transformer_single.py:85

↓ 1 callersFunctiongeneralized_box_iou

Generalized IoU from https://giou.stanford.edu/ The boxes should be in [x0, y0, x1, y1] format Returns a [N, M] pairwise matrix, w

util/box_ops.py:48

↓ 1 callersFunctionget_args_parser

()

main.py:28

↓ 1 callersFunctionget_benckmark_arg_parser

()

benchmark.py:22

↓ 1 callersFunctionget_extensions

()

models/ops/setup.py:23

↓ 1 callersMethodget_img_ids_from_vid

Get image ids from given video id. Args: vidId (int): The given video id. Returns: list[int]: Image ids of

datasets/coco_video_parser.py:105

↓ 1 callersMethodget_proposal_pos_embed

(self, proposals)

models/deformable_transformer_multi.py:85

↓ 1 callersMethodget_proposal_pos_embed

(self, proposals)

models/deformable_transformer_single.py:70

↓ 1 callersFunctionget_rank

()

util/misc.py:396

↓ 1 callersFunctionget_rank

()

util/misc_multi.py:417

↓ 1 callersMethodget_reference_points

(spatial_shapes, valid_ratios, device)

models/deformable_transformer_multi.py:142

↓ 1 callersMethodget_reference_points

(spatial_shapes, valid_ratios, device)

models/deformable_transformer_multi.py:437

↓ 1 callersMethodget_reference_points

(spatial_shapes, valid_ratios, device)

models/deformable_transformer_single.py:239

↓ 1 callersFunctionget_size

(image_size, size, max_size=None)

datasets/transforms_multi.py:140

↓ 1 callersFunctionget_size

(image_size, size, max_size=None)

datasets/transforms_single.py:107

↓ 1 callersFunctionget_size_with_aspect_ratio

(image_size, size, max_size=None)

datasets/transforms_multi.py:120

↓ 1 callersFunctionget_size_with_aspect_ratio

(image_size, size, max_size=None)

datasets/transforms_single.py:87

↓ 1 callersMethodget_valid_ratio

(self, mask)

models/deformable_transformer_multi.py:132

↓ 1 callersMethodget_valid_ratio

(self, mask)

models/deformable_transformer_single.py:117

↓ 1 callersFunctionhflip

(clip, target)

datasets/transforms_multi.py:83

↓ 1 callersFunctionhflip

(image, target)

datasets/transforms_single.py:67

↓ 1 callersFunctioninterpolate

Equivalent to nn.functional.interpolate, but with support for empty batch sizes. This will eventually be supported natively by PyTorch, and

util/misc_multi.py:505

↓ 1 callersFunctioninverse_sigmoid

(x, eps=1e-5)

util/misc_multi.py:535

↓ 1 callersFunctionis_main_process

()

util/misc_multi.py:435

↓ 1 callersFunctionmain

(args)

main.py:137

↓ 1 callersFunctionmain

()

tools/launch.py:159

↓ 1 callersFunctionmake_coco_transforms

(image_set)

datasets/vid_single.py:143

↓ 1 callersFunctionmake_coco_transforms

(image_set)

datasets/vid_multi.py:210

↓ 1 callersFunctionmasks_to_boxes

Compute the bounding boxes around the provided masks The masks should be in format [N, H, W] where N is the number of masks, (H, W) are the spa

util/box_ops.py:72

↓ 1 callersFunctionmeasure_average_inference_time

(model, inputs, num_iters=100, warm_iters=5)

benchmark.py:32

↓ 1 callersFunctionmerge

(img_ids, eval_imgs)

datasets/coco_eval.py:178

↓ 1 callersFunctionpad

(clip, target, padding)

datasets/transforms_multi.py:180

↓ 1 callersFunctionpad

(image, target, padding)

datasets/transforms_single.py:143

↓ 1 callersFunctionparse_args

Helper function parsing the command line options @retval ArgumentParser

tools/launch.py:116

↓ 1 callersMethodprepare_for_coco_detection

(self, predictions)

datasets/coco_eval.py:87

↓ 1 callersMethodprepare_for_coco_keypoint

(self, predictions)

datasets/coco_eval.py:146

↓ 1 callersMethodprepare_for_coco_segmentation

(self, predictions)

datasets/coco_eval.py:111

↓ 1 callersMethodreset_parameters

(self)

models/position_encoding.py:69

↓ 1 callersFunctionresize

(clip, target, size, max_size=None)

datasets/transforms_multi.py:117

↓ 1 callersFunctionresize

(image, target, size, max_size=None)

datasets/transforms_single.py:84

↓ 1 callersMethodset_epoch

(self, epoch)

datasets/samplers.py:71

↓ 1 callersFunctionsetup_for_distributed

This function disables printing when not in master process

util/misc.py:367

↓ 1 callersFunctionsetup_for_distributed

This function disables printing when not in master process

util/misc_multi.py:388

↓ 1 callersFunctiontrain_one_epoch

(model: torch.nn.Module, criterion: torch.nn.Module, data_loader: Iterable, optimizer: to

engine_multi.py:24

↓ 1 callersFunctionvflip

(image,target)

datasets/transforms_multi.py:101

↓ 1 callersMethodwith_pos_embed

(tensor, pos)

models/deformable_transformer_multi.py:409

↓ 1 callersMethodwith_pos_embed

(tensor, pos)

models/deformable_transformer_single.py:211

FunctionPYBIND11_MODULE

models/ops/src/vision.cpp:13

Method__call__

(self, image, target)

datasets/vid_single.py:82

Method__call__

(self, img, target)

datasets/transforms_multi.py:199

Method__call__

(self, img: PIL.Image.Image, target: dict)

datasets/transforms_multi.py:209

Method__call__

(self, img, target)

datasets/transforms_multi.py:220

Method__call__

(self, img, target)

datasets/transforms_multi.py:234

Method__call__

(self, image, target)

datasets/transforms_multi.py:290

Method__call__

(self, image, target)

datasets/transforms_multi.py:302

Method__call__

(self, image, target)

datasets/transforms_multi.py:315

Method__call__

(self, image, target)

datasets/transforms_multi.py:325

Method__call__

(self, image, target)

datasets/transforms_multi.py:337

Method__call__

(self, image, target)

datasets/transforms_multi.py:349

Method__call__

(self, image)

datasets/transforms_multi.py:361

Method__call__

(self,clip,target)

datasets/transforms_multi.py:378

Method__call__

(self, clip, target)

datasets/transforms_multi.py:396

Method__call__

(self, img, target)

datasets/transforms_multi.py:426

Method__call__

(self, img, target)

datasets/transforms_multi.py:435

Method__call__

(self, img, target=None)

datasets/transforms_multi.py:447

Method__call__

(self, img, target)

datasets/transforms_multi.py:456

Method__call__

(self, img, target)

datasets/transforms_multi.py:472

Method__call__

(self, clip, target)

datasets/transforms_multi.py:479

Method__call__

(self, img, target)

datasets/transforms_multi.py:491

Method__call__

(self, clip, target=None)

datasets/transforms_multi.py:500

Method__call__

(self, image, target)

datasets/transforms_multi.py:520

Method__call__

(self, img, target)

datasets/transforms_single.py:160

Method__call__

(self, img: PIL.Image.Image, target: dict)

datasets/transforms_single.py:170

Method__call__

(self, img, target)

datasets/transforms_single.py:181

Method__call__

(self, img, target)

datasets/transforms_single.py:193

Method__call__

(self, img, target=None)

datasets/transforms_single.py:205

Method__call__

(self, img, target)

datasets/transforms_single.py:214

Method__call__

(self, img, target)

datasets/transforms_single.py:230

Method__call__

(self, img, target)

datasets/transforms_single.py:237

← previous next →101–200 of 415, ranked by callers