Functions — github.com/IDEA-Research/DINO

hub / github.com/IDEA-Research/DINO / functions

Functions501 in github.com/IDEA-Research/DINO

⨍ Functions 501◇ Types & classes 105

↓ 1 callersMethod_get_tgt_permutation_idx

(self, indices)

models/dino/dino.py:458

↓ 1 callersFunction_is_power_of_2

(n)

models/dino/ops/modules/ms_deform_attn.py:24

↓ 1 callersFunction_max_by_axis

(the_list)

util/misc.py:292

↓ 1 callersFunction_onnx_nested_tensor_from_tensor_list

(tensor_list: List[Tensor])

util/misc.py:403

↓ 1 callersMethod_parse_int_float_bool

(val)

util/slconfig.py:416

↓ 1 callersMethod_reset_parameters

(self)

models/dino/transformer_deformable.py:72

↓ 1 callersMethod_reset_parameters

(self)

models/dino/deformable_transformer.py:225

↓ 1 callersMethod_reset_parameters

(self)

models/dino/dino.py:188

↓ 1 callersMethod_reset_parameters

(self)

models/dino/attention.py:111

↓ 1 callersMethod_reset_parameters

(self)

models/dino/ops/modules/ms_deform_attn.py:62

↓ 1 callersMethod_setup_gpu_args

(self)

run_with_submitit.py:70

↓ 1 callersMethod_validate_py_syntax

(filename)

util/slconfig.py:71

↓ 1 callersMethodaccumulate

(self)

datasets/coco_eval.py:63

↓ 1 callersFunctionaccuracy

Computes the precision@k for the specified values of k

util/misc.py:522

↓ 1 callersMethodaddtgt

- tgt: dict. args: - boxes: num_boxes, 4. xywh, [0,1]. - box_label: num_boxes.

util/visualizer.py:88

↓ 1 callersFunctionbenchmark

()

tools/benchmark.py:607

↓ 1 callersFunctionbox_iou_pairwise

(boxes1, boxes2)

util/box_ops.py:68

↓ 1 callersFunctionbuild

(image_set, args)

datasets/coco.py:612

↓ 1 callersFunctionbuild_backbone

Useful args: - backbone: backbone name - lr_backbone: - dilation - return_interm_indices: available: [0,1,2,3],

models/dino/backbone.py:147

↓ 1 callersFunctionbuild_convnext

(modelname, pretrained,backbone_dir=None, **kw)

models/dino/convnext.py:234

↓ 1 callersFunctionbuild_deformable_transformer

(args)

models/dino/deformable_transformer.py:1004

↓ 1 callersFunctionbuild_matcher

(args)

models/dino/matcher.py:178

↓ 1 callersFunctionbuild_position_encoding

(args)

models/dino/position_encoding.py:138

↓ 1 callersFunctioncheck_file_exist

(filename, msg_tmpl='file "{}" does not exist')

util/slconfig.py:24

↓ 1 callersFunctioncheck_forward_equal_with_pytorch_double

()

models/dino/ops/test.py:32

↓ 1 callersFunctioncheck_forward_equal_with_pytorch_float

()

models/dino/ops/test.py:48

↓ 1 callersFunctioncheck_gradient_numerical

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

models/dino/ops/test.py:63

↓ 1 callersFunctioncheck_keep

(keyname, ignorekeywordlist)

main.py:232

↓ 1 callersMethodcheckpoint

(self)

run_with_submitit.py:59

↓ 1 callersFunctionciou

(bboxes1, bboxes2)

util/box_loss.py:7

↓ 1 callersFunctionclean_state_dict

(state_dict)

util/misc.py:581

↓ 1 callersFunctionconv_flop_count

This method counts the flops for convolution. Note only multiplication is counted. Computation for addition and bias is ignored. Args:

tools/benchmark.py:160

↓ 1 callersFunctionconvert_coco_poly_to_mask

(segmentations, height, width)

datasets/coco.py:372

↓ 1 callersFunctioncreate_common_coco_eval

(coco_eval, img_ids, eval_imgs)

datasets/coco_eval.py:205

↓ 1 callersMethodcreate_embedding_fn

(self)

util/utils.py:128

↓ 1 callersFunctiondice_loss

Compute the DICE loss, similar to generalized IOU for masks Args: inputs: A float tensor of arbitrary shape. The pred

models/dino/segmentation.py:184

↓ 1 callersFunctiondiou

(bboxes1, bboxes2)

util/box_loss.py:58

↓ 1 callersFunctiondn_post_process

post process of dn after output from the transformer put the dn part in the dn_meta

models/dino/dn_components.py:140

↓ 1 callersMethoddump_to_fileobj

(self, obj, file, **kwargs)

util/slio.py:25

↓ 1 callersMethoddump_to_fileobj

(self, obj, file, **kwargs)

util/slio.py:45

↓ 1 callersMethoddump_to_path

(self, obj, filepath, **kwargs)

util/slio.py:68

↓ 1 callersMethoddump_to_str

(self, obj, **kwargs)

util/slio.py:48

↓ 1 callersMethodembed

(self, inputs)

util/utils.py:152

↓ 1 callersFunctionensure_rng

Coerces input into a random number generator. If the input is None, then a global random state is returned. If the input is a numeric value,

util/utils.py:306

↓ 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:221

↓ 1 callersMethodfinal_res

(self)

util/time_counter.py:28

↓ 1 callersFunctionfind_IoU

Find IoU between every boxes set of boxes boxes1: a tensor of dimensions (n1, 4) (left, top, right , bottom) boxes2: a tenso

datasets/random_crop.py:27

↓ 1 callersFunctionflop_count

Given a model and an input to the model, compute the Gflops of the given model. Note the input should have a batch size of 1. Args:

tools/benchmark.py:476

↓ 1 callersMethodforward_ca

(self, # for tgt tgt: Optional[Tensor], # nq, bs, d_model tg

models/dino/transformer_deformable.py:440

↓ 1 callersMethodforward_ca

(self, # for tgt tgt: Optional[Tensor], # nq, bs, d_model tgt

models/dino/deformable_transformer.py:922

↓ 1 callersMethodforward_features

(self, x)

models/dino/convnext.py:121

↓ 1 callersMethodforward_ffn

(self, src)

models/dino/transformer_deformable.py:256

↓ 1 callersMethodforward_ffn

(self, tgt)

models/dino/transformer_deformable.py:388

↓ 1 callersMethodforward_ffn

(self, src)

models/dino/deformable_transformer.py:801

↓ 1 callersMethodforward_ffn

(self, tgt)

models/dino/deformable_transformer.py:873

↓ 1 callersMethodforward_sa

(self, # for tgt tgt: Optional[Tensor], # nq, bs, d_model tg

models/dino/transformer_deformable.py:394

↓ 1 callersMethodforward_sa

(self, # for tgt tgt: Optional[Tensor], # nq, bs, d_model tgt

models/dino/deformable_transformer.py:879

↓ 1 callersMethodgen_encoder_output_proposals

(self, memory, memory_padding_mask, spatial_shapes)

models/dino/transformer_deformable.py:99

↓ 1 callersMethodgenerate_pertube_samples

(self)

datasets/coco.py:196

↓ 1 callersFunctionget_args_parser

()

main.py:27

↓ 1 callersFunctionget_aux_target_hacks_list

(image_set, args)

datasets/coco.py:554

↓ 1 callersFunctionget_extensions

()

models/dino/ops/setup.py:23

↓ 1 callersFunctionget_init_file

()

run_with_submitit.py:42

↓ 1 callersFunctionget_param_dict

(args, model_without_ddp: nn.Module)

util/get_param_dicts.py:15

↓ 1 callersMethodget_proposal_pos_embed

(self, proposals)

models/dino/transformer_deformable.py:84

↓ 1 callersFunctionget_rank

()

util/misc.py:460

↓ 1 callersMethodget_reference_points

(spatial_shapes, valid_ratios, device)

models/dino/transformer_deformable.py:291

↓ 1 callersMethodget_reference_points

(spatial_shapes, valid_ratios, device)

models/dino/deformable_transformer.py:477

↓ 1 callersFunctionget_size

(image_size, size, max_size=None)

datasets/transforms.py:100

↓ 1 callersFunctionget_size_with_aspect_ratio

(image_size, size, max_size=None)

datasets/transforms.py:80

↓ 1 callersMethodget_valid_ratio

(self, mask)

models/dino/transformer_deformable.py:131

↓ 1 callersMethodget_valid_ratio

(self, mask)

models/dino/deformable_transformer.py:238

↓ 1 callersFunctionhflip

(image, target)

datasets/transforms.py:60

↓ 1 callersMethodinit_ref_points

(self, use_num_queries)

models/dino/deformable_transformer.py:247

↓ 1 callersMethodinit_ref_points

(self, use_num_queries)

models/dino/dino.py:194

↓ 1 callersFunctionintersect

Find intersection of every box combination between two sets of box boxes1: bounding boxes 1, a tensor of dimensions (n1, 4) b

datasets/random_crop.py:9

↓ 1 callersMethodisbetter

(self, new_res, old_res)

util/utils.py:407

↓ 1 callersFunctionkey_select_function

(keyname)

models/dino/backbone.py:196

↓ 1 callersFunctionlighting_noise

color channel swap in image image: A PIL image

datasets/sltransform.py:38

↓ 1 callersMethodload_from_fileobj

(self, file, **kwargs)

util/slio.py:21

↓ 1 callersMethodload_from_fileobj

(self, file)

util/slio.py:42

↓ 1 callersMethodload_from_path

(self, filepath, **kwargs)

util/slio.py:56

↓ 1 callersFunctionmain

()

run_with_submitit.py:83

↓ 1 callersFunctionmain

(args)

main.py:86

↓ 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 spati

util/box_ops.py:108

↓ 1 callersFunctionmeasure_time

(model, inputs, N=10)

tools/benchmark.py:587

↓ 1 callersFunctionmerge

(img_ids, eval_imgs)

datasets/coco_eval.py:183

↓ 1 callersFunctionparse_args

()

run_with_submitit.py:14

↓ 1 callersMethodprep_for_dn

(self,dn_meta)

models/dino/dino.py:630

↓ 1 callersFunctionprepare_for_cdn

A major difference of DINO from DN-DETR is that the author process pattern embedding pattern embedding in its detector forward functi

models/dino/dn_components.py:20

↓ 1 callersMethodprepare_for_coco_detection

(self, predictions)

datasets/coco_eval.py:82

↓ 1 callersMethodprepare_for_coco_keypoint

(self, predictions)

datasets/coco_eval.py:151

↓ 1 callersMethodprepare_for_coco_segmentation

(self, predictions)

datasets/coco_eval.py:116

↓ 1 callersFunctionpreparing_dataset

(pathdict, image_set, args)

datasets/data_util.py:117

↓ 1 callersFunctionrenorm

(img: torch.FloatTensor, mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])

util/visualizer.py:23

↓ 1 callersMethodreset

(self)

util/time_counter.py:43

↓ 1 callersMethodreset_parameters

(self)

models/dino/position_encoding.py:120

↓ 1 callersMethodrm_self_attn_modules

(self)

models/dino/deformable_transformer.py:864

↓ 1 callersFunctionrotate

Rotate image and bounding box image: A Pil image (w, h) boxes: A tensors of dimensions (#objects, 4) Out: ro

datasets/sltransform.py:60

↓ 1 callersMethodsample_for_pred_first_item

(self, box_label: torch.FloatTensor)

datasets/coco.py:120

← previous next →101–200 of 501, ranked by callers