Functions — github.com/Banconxuan/RTM3D

CodeHub MCPcopy Create free account

hub / github.com/Banconxuan/RTM3D / functions

Functions537 in github.com/Banconxuan/RTM3D

⨍ Functions 537◇ Types & classes 86

↓ 42 callersFunction_transpose_and_gather_feat

src/lib/models/utils.py:22

↓ 27 callersFunction_gather_feat

(feat, ind, mask=None)

src/lib/models/utils.py:12

↓ 23 callersMethodmsg

src/tools/kitti_eval/mail.h:30

↓ 15 callersFunction_nms

(heat, kernel=3)

src/lib/models/decode.py:9

↓ 15 callersFunctionprint_str

(value, *arg, sstream=None)

src/tools/kitti-object-eval-python/eval.py:570

↓ 14 callersMethodwrite

src/lib/logger.py:65

↓ 13 callersFunction_topk

src/lib/models/decode.py:103

↓ 11 callersMethod__init__

(self, levels, channels, num_classes=1000, block=BasicBlock, residual_root=False, linear_root

src/lib/models/networks/pose_dla_dcn.py:225

↓ 11 callersFunctionarea

(int_pts, num_of_inter)

src/tools/kitti-object-eval-python/rotate_iou.py:23

↓ 10 callersMethod__init__

src/lib/models/losses.py:257

↓ 10 callersMethodload_pretrained_model

(self, data='imagenet', name='dla34', hash='ba72cf86')

src/lib/models/networks/dlav0.py:304

↓ 10 callersMethodupdate

(self, val, n=1)

src/lib/utils/utils.py:18

↓ 9 callersMethod__init__

(self, levels, channels, num_classes=1000, block=BasicBlock, residual_root=False, return_leve

src/lib/models/networks/dlav0.py:222

↓ 9 callersFunctioneval_class

src/tools/kitti_eval/evaluate_object_3d_offline.cpp:621

↓ 9 callersFunctioneval_class

src/tools/kitti_eval/evaluate_object_3d.cpp:620

↓ 7 callersMethodadd_blend_img

(self, back, fore, img_id='blend', trans=0.7)

src/lib/utils/debugger.py:130

↓ 7 callersMethodgather

(self, outputs, output_device)

src/lib/models/data_parallel.py:83

↓ 7 callersFunctionget_affine_transform

(center, scale, rot, output_size,

src/lib/utils/image.py:27

↓ 7 callersFunctiontransform_preds

(coords, center, scale, output_size)

src/lib/utils/image.py:19

↓ 6 callersFunctionE2R

Combine Euler angles to the rotation matrix (right-hand) Inputs: Ry, Rx, Rz : rotation angles along y, x, z axis

src/lib/utils/kitti_read.py:69

↓ 6 callersFunction_extend_matrix

src/tools/kitti-object-eval-python/kitti_common.py:55

↓ 6 callersMethodadd_coco_bbox

(self, bbox, cat, conf=1, show_txt=True, img_id='default')

src/lib/utils/debugger.py:215

↓ 6 callersFunctioncompute_box_3d

(dim, location, rotation_y)

src/lib/utils/ddd_utils.py:8

↓ 5 callersFunctionNormalizeVector

src/lib/utils/kitti_read.py:113

↓ 5 callersFunctionSpace2Bev

(P0, side_range=(-20, 20), fwd_range=(0, 70), res=0.1)

src/lib/utils/vis_3d_utils.py:25

↓ 5 callersFunctionSpace2Image

Project a 3D point to the image Inputs: P0 : Camera intrinsic matrix 3 x 4 pts3 : 4-d homogeneous coordinates

src/lib/utils/kitti_read.py:91

↓ 5 callersMethod__init__

( self, n, nstack, dims, modules, heads, pre=None, cnv_dim=256, make_tl_layer=None, make_br_l

src/lib/models/networks/large_hourglass.py:177

↓ 5 callersMethodbackward

(ctx, grad_output)

src/lib/models/networks/DCNv2/dcn_v2.py:37

↓ 5 callersFunctionintersection

Compute pairwise intersection areas between boxes. Args: boxes1: a numpy array with shape [N, 4] holding N boxes boxes2: a numpy

src/tools/kitti-object-eval-python/kitti_common.py:366

↓ 5 callersFunctionsave_model

(path, epoch, model, optimizer=None)

src/lib/models/model.py:87

↓ 4 callersFunction_h_aggregate

(heat, aggr_weight=0.1)

src/lib/models/decode.py:71

↓ 4 callersMethod_make_layer

(self, block, planes, blocks, stride=1)

src/lib/models/networks/msra_resnet.py:156

↓ 4 callersMethod_make_layer

(self, block, planes, blocks, stride=1)

src/lib/models/networks/resnet_dcn.py:179

↓ 4 callersFunction_v_aggregate

(heat, aggr_weight=0.1)

src/lib/models/decode.py:75

↓ 4 callersFunctionaffine_transform

src/lib/utils/image.py:63

↓ 4 callersFunctioncompute_res_loss

(output, target)

src/lib/models/losses.py:289

↓ 4 callersFunctionget_kitti_info_path

(idx, prefix, info_type='image_2', fil

src/tools/kitti-object-eval-python/kitti_common.py:14

↓ 4 callersFunctionget_mAP

src/tools/kitti-object-eval-python/eval.py:556

↓ 4 callersFunctionget_mAP_R40

src/tools/kitti-object-eval-python/eval.py:563

↓ 4 callersFunctionsaveAndPlotPlots

src/tools/kitti_eval/evaluate_object_3d_offline.cpp:707

↓ 4 callersFunctionsaveAndPlotPlots

src/tools/kitti_eval/evaluate_object_3d.cpp:706

↓ 4 callersFunctiontoPolygon

src/tools/kitti_eval/evaluate_object_3d_offline.cpp:270

↓ 4 callersFunctiontoPolygon

src/tools/kitti_eval/evaluate_object_3d.cpp:270

↓ 4 callersFunctiontrangle_area

src/tools/kitti-object-eval-python/rotate_iou.py:17

↓ 3 callersMethod__init__

(self, in_channels, out_channels, kernel_size, stride, padding, dilation=1,

src/lib/models/networks/DCNv2/dcn_v2.py:99

↓ 3 callersMethodadd_img

(self, img, img_id='default', revert_color=False)

src/lib/utils/debugger.py:96

↓ 3 callersFunctioncar_pose_decode

( heat, wh, kps,dim,rot, prob=None,reg=None, hm_hp=None, hp_offset=None, K=100,meta=None,const=None)

src/lib/models/decode.py:680

↓ 3 callersMethodclose

src/lib/logger.py:76

↓ 3 callersFunctioneval_class

Kitti eval. support 2d/bev/3d/aos eval. support 0.5:0.05:0.95 coco AP. Args: gt_annos: dict, must from get_label_annos() in kitti_common.p

src/tools/kitti-object-eval-python/eval.py:448

↓ 3 callersFunctionexp_rampup

Exponential rampup from https://arxiv.org/abs/1610.02242

src/lib/trains/base_trainer.py:12

↓ 3 callersMethodgen_colormap

(self, img, output_res=None)

src/lib/utils/debugger.py:161

↓ 3 callersMethodgen_colormap_hp

(self, img, output_res=None)

src/lib/utils/debugger.py:192

↓ 3 callersMethodinit

(self, args='')

src/lib/opts.py:330

↓ 3 callersFunctionproject_to_image

(pts_3d, P,img_shape)

src/lib/utils/ddd_utils.py:25

↓ 3 callersMethodrun

(self, image_or_path_or_tensor, meta=None)

src/lib/detectors/base_detector.py:100

↓ 2 callersMethod__init__

(self, inplanes, planes, stride=1, downsample=None)

src/lib/models/networks/msra_resnet.py:39

↓ 2 callersMethod__init__

(self, inplanes, planes, stride=1, downsample=None)

src/lib/models/networks/resnet_dcn.py:41

↓ 2 callersMethod__len__

src/lib/datasets/dataset/kittihp.py:71

↓ 2 callersMethod_get_border

(self, border, size)

src/lib/datasets/sample/car_pose.py:26

↓ 2 callersMethod_make_conv_level

(self, inplanes, planes, convs, stride=1, dilation=1)

src/lib/models/networks/dlav0.py:277

↓ 2 callersMethod_make_conv_level

(self, inplanes, planes, convs, stride=1, dilation=1)

src/lib/models/networks/pose_dla_dcn.py:274

↓ 2 callersFunction_sigmoid

src/lib/models/utils.py:8

↓ 2 callersFunction_topk_channel

src/lib/models/decode.py:92

↓ 2 callersMethodadd_coco_hp

(self, points, img_id='default')

src/lib/utils/debugger.py:235

↓ 2 callersFunctionalpha2rot_y

Get rotation_y by alpha + theta - 180 alpha : Observation angle of object, ranging [-pi..pi] x : Object center x to the camera center (x-

src/lib/utils/ddd_utils.py:124

↓ 2 callersFunctionarea

Computes area of boxes. Args: boxes: Numpy array with shape [N, 4] holding N boxes Returns: a numpy array with shape [N*1] r

src/tools/kitti-object-eval-python/kitti_common.py:350

↓ 2 callersFunctionblend_

(alpha, image1, image2)

src/lib/utils/image.py:205

↓ 2 callersFunctioncar_pose_post_process

(dets, c, s, h, w)

src/lib/utils/post_process.py:115

↓ 2 callersFunctioncomputeStatistics

src/tools/kitti_eval/evaluate_object_3d_offline.cpp:457

↓ 2 callersFunctioncomputeStatistics

src/tools/kitti_eval/evaluate_object_3d.cpp:456

↓ 2 callersFunctioncompute_bin_loss

(output, target, mask)

src/lib/models/losses.py:294

↓ 2 callersFunctioncompute_statistics_jit

(overlaps, gt_datas, dt_datas,

src/tools/kitti-object-eval-python/eval.py:158

↓ 2 callersFunctionconv3x3

3x3 convolution with padding

src/lib/models/networks/msra_resnet.py:30

↓ 2 callersFunctionconv3x3

3x3 convolution with padding

src/lib/models/networks/resnet_dcn.py:32

↓ 2 callersFunctioncreate_model

(arch, heads, head_conv)

src/lib/models/model.py:24

↓ 2 callersFunctiondiv_up

src/tools/kitti-object-eval-python/rotate_iou.py:13

↓ 2 callersFunctiondo_eval

(gt_annos, dt_annos, current_classes, min_overlaps, compute_ao

src/tools/kitti-object-eval-python/eval.py:579

↓ 2 callersFunctiondraw_box_3d

(image, corners, c=(0, 0, 255))

src/lib/utils/ddd_utils.py:96

↓ 2 callersFunctionfill_fc_weights

src/lib/models/networks/dlav0.py:524

↓ 2 callersFunctionfill_fc_weights

src/lib/models/networks/resnet_dcn.py:121

↓ 2 callersFunctionfill_fc_weights

src/lib/models/networks/pose_dla_dcn.py:326

↓ 2 callersFunctionflip_tensor

src/lib/models/utils.py:28

↓ 2 callersFunctiongaussian2D

(shape, sigma=1)

src/lib/utils/image.py:118

↓ 2 callersFunctiongaussian_radius

(det_size, min_overlap=0.7)

src/lib/utils/image.py:95

↓ 2 callersFunctiongen_position

(kps,dim,rot,meta,const)

src/lib/models/decode.py:576

↓ 2 callersFunctionget_3rd_point

src/lib/utils/image.py:69

↓ 2 callersFunctionget_image_index_str

src/tools/kitti-object-eval-python/kitti_common.py:10

↓ 2 callersFunctionget_label_anno

src/tools/kitti-object-eval-python/kitti_common.py:293

↓ 2 callersFunctionget_split_parts

(num, num_part)

src/tools/kitti-object-eval-python/eval.py:278

↓ 2 callersFunctionimage_box_overlap

(boxes, query_boxes, criterion=-1)

src/tools/kitti-object-eval-python/eval.py:87

↓ 2 callersFunctionload_model

(model, model_path, optimizer=None, resume=False, lr=None, lr_step=None)

src/lib/models/model.py:31

↓ 2 callersMethodparse

(self, args='')

src/lib/opts.py:239

↓ 2 callersFunctionpoint_in_quadrilateral

(pt_x, pt_y, corners)

src/tools/kitti-object-eval-python/rotate_iou.py:161

↓ 2 callersMethodproject_3d_to_bird

src/lib/utils/debugger.py:417

↓ 2 callersFunctionrbbox_to_corners

(corners, rbbox)

src/tools/kitti-object-eval-python/rotate_iou.py:204

↓ 2 callersFunctionrotate_iou_gpu_eval

rotated box iou running in gpu. 500x faster than cpu version (take 5ms in one example with numba.cuda code). convert from [this project](

src/tools/kitti-object-eval-python/rotate_iou.py:294

↓ 2 callersMethodrun_epoch

(self, phase, epoch, data_loader,unlabel_loader1=None,unlabel_loader2=None,unlabel_set=None,iter_num=None,data

src/lib/trains/base_trainer.py:68

↓ 2 callersMethodscalar_summary

Log a scalar variable.

src/lib/logger.py:79

↓ 2 callersFunctionscatter

r""" Slices variables into approximately equal chunks and distributes them across given GPUs. Duplicates references to objects that are no

src/lib/models/scatter_gather.py:6

↓ 2 callersFunctionscatter_kwargs

r"""Scatter with support for kwargs dictionary

src/lib/models/scatter_gather.py:28

next →1–100 of 537, ranked by callers