Functions — github.com/NVlabs/CenterPose

CodeHub MCPcopy Create free account

hub / github.com/NVlabs/CenterPose / functions

Functions615 in github.com/NVlabs/CenterPose

⨍ Functions 615◇ Types & classes 95

↓ 2 callersMethod_intersect

Computes the intersection of a line with an axis-aligned plane. Args: plane: Formulated as two 3D points on the plane. pr

src/tools/objectron_eval/objectron/dataset/iou.py:162

↓ 2 callersMethod_make_conv_level

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

src/lib/models/networks/dlav0.py:298

↓ 2 callersMethod_make_conv_level

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

src/lib/models/networks/pose_dla_dcn.py:298

↓ 2 callersFunction_sigmoid

src/lib/models/utils.py:9

↓ 2 callersFunction_topk

src/lib/models/decode.py:52

↓ 2 callersFunction_topk_channel

src/lib/models/decode.py:40

↓ 2 callersMethodadd_coco_hp_paper

(self, bbox, points, std=None, img_id='default')

src/lib/utils/debugger.py:195

↓ 2 callersMethodapply_transformation

Applies transformation on the box. Group multiplication is the same as rotation concatenation. Therefore return new box with SE3(R * R2, T +

data/objectron/dataset/box.py:87

↓ 2 callersMethodapply_transformation

Applies transformation on the box. Group multiplication is the same as rotation concatenation. Therefore return new box with SE3(R *

src/tools/objectron_eval/objectron/dataset/box.py:91

↓ 2 callersFunctionblend_

(alpha, image1, image2)

src/lib/utils/image.py:248

↓ 2 callersFunctionbounding_box

src/tools/objectron_eval/eval_video_official.py:117

↓ 2 callersFunctionbounding_box_rotation

(points, trans)

src/lib/datasets/dataset_combined.py:46

↓ 2 callersMethodcompute_average_distance

Computes Average Distance (ADD) metric.

src/tools/objectron_eval/eval_video_official.py:1276

↓ 2 callersMethodcompute_average_distance

Computes Average Distance (ADD) metric.

src/tools/objectron_eval/eval_image_official.py:924

↓ 2 callersFunctioncompute_bin_loss

(output, target, mask)

src/lib/models/losses.py:284

↓ 2 callersMethodcompute_viewpoint

Computes viewpoint of a 3D bounding box. We use the definition of polar angles in spherical coordinates (http://mathworld.wolfram.com/PolarAn

data/objectron/dataset/eval.py:269

↓ 2 callersMethodcompute_viewpoint

Computes viewpoint of a 3D bounding box. We use the definition of polar angles in spherical coordinates (http://mathworld.wolfram.com

src/tools/objectron_eval/eval_video_official.py:1301

↓ 2 callersMethodcompute_viewpoint

Computes viewpoint of a 3D bounding box. We use the definition of polar angles in spherical coordinates (http://mathworld.wolfram.com

src/tools/objectron_eval/eval_image_official.py:949

↓ 2 callersMethodcompute_viewpoint

Computes viewpoint of a 3D bounding box. We use the definition of polar angles in spherical coordinates (http://mathworld.wolfram.com

src/tools/objectron_eval/objectron/dataset/eval.py:268

↓ 2 callersFunctionconv3x3

3x3 convolution with padding

src/lib/models/networks/msra_resnet.py:29

↓ 2 callersFunctionconv3x3

3x3 convolution with padding

src/lib/models/networks/resnet_dcn.py:33

↓ 2 callersMethodconvert_rvec_to_quaternion

Convert rvec (which is log quaternion) to quaternion

src/lib/utils/pnp/cuboid_pnp_solver.py:241

↓ 2 callersFunctiondmcn_im2col_bilinear_cpu

src/lib/models/networks/DCNv2/src/cpu/dcn_v2_im2col_cpu.cpp:27

↓ 2 callersFunctiondraw_axes

(image_debug, box, projection_matrix, height, width, c=None)

src/tools/objectron_eval/eval_utils.py:11

↓ 2 callersFunctiondraw_face

(object_id, face, color)

data/objectron/dataset/graphics.py:42

↓ 2 callersFunctiondraw_face

(object_id, face, color)

src/tools/objectron_eval/objectron/dataset/graphics.py:42

↓ 2 callersMethodevaluate

Evaluates a batch of serialized tf.Example protos.

data/objectron/dataset/eval.py:91

↓ 2 callersMethodevaluate

Evaluates a batch of serialized tf.Example protos.

src/tools/objectron_eval/eval_video_official.py:502

↓ 2 callersMethodevaluate

Evaluates a batch of serialized tf.Example protos.

src/tools/objectron_eval/eval_image_official.py:243

↓ 2 callersMethodevaluate

Evaluates a batch of serialized tf.Example protos.

src/tools/objectron_eval/objectron/dataset/eval.py:92

↓ 2 callersMethodevaluate_2d

Evaluates a pair of 2D projections of 3D boxes. It computes the mean normalized distances of eight vertices of a box. Args:

src/tools/objectron_eval/eval_video_official.py:1017

↓ 2 callersMethodevaluate_2d

Evaluates a pair of 2D projections of 3D boxes. It computes the mean normalized distances of eight vertices of a box. Args:

src/tools/objectron_eval/eval_image_official.py:673

↓ 2 callersMethodevaluate_3d

Evaluates a box in 3D. It computes metrics of view angle and 3D IoU. Args: box: A predicted box. instance_3d: A

src/tools/objectron_eval/eval_video_official.py:1084

↓ 2 callersMethodevaluate_3d

Evaluates a box in 3D. It computes metrics of view angle and 3D IoU. Args: box: A predicted box. instance_3d: A

src/tools/objectron_eval/eval_image_official.py:739

↓ 2 callersMethodevaluate_iou

Evaluates a 3D box by 3D IoU. It computes 3D IoU of predicted and annotated boxes. Args: box: A 9*3 array of a predicted b

src/tools/objectron_eval/eval_video_official.py:1403

↓ 2 callersMethodevaluate_viewpoint

Evaluates a 3D box by viewpoint. Args: box: A 9*3 array of a predicted box. instance: A 9*3 array of an annotated box, in

src/tools/objectron_eval/eval_video_official.py:1320

↓ 2 callersMethodevaluate_viewpoint

Evaluates a 3D box by viewpoint. Args: box: A 9*3 array of a predicted box. instance: A 9*3 array of an annotated box, in

src/tools/objectron_eval/eval_image_official.py:968

↓ 2 callersFunctionfill_fc_weights

src/lib/models/networks/dlav0.py:554

↓ 2 callersFunctionfill_fc_weights

src/lib/models/networks/resnet_dcn.py:124

↓ 2 callersFunctionfill_fc_weights

src/lib/models/networks/pose_dla_dcn.py:358

↓ 2 callersMethodfinalize

Computes average precision curves.

src/tools/objectron_eval/eval_video_official.py:1527

↓ 2 callersFunctiongaussian

Returns a gaussian function with the given parameters

src/lib/utils/gpfit.py:5

↓ 2 callersFunctiongaussian2D

(shape, sigma=1)

src/lib/utils/image.py:126

↓ 2 callersFunctiongen_oracle_map

(feat, ind, w, h)

src/lib/utils/oracle_utils.py:10

↓ 2 callersFunctionget_3rd_point

src/lib/utils/image.py:77

↓ 2 callersMethodget_vertices

src/lib/utils/pnp/cuboid_objectron.py:77

↓ 2 callersMethodinit_kf

src/lib/utils/tracker_baseline.py:55

↓ 2 callersMethodinit_kf

src/lib/utils/tracker.py:55

↓ 2 callersFunctionmodulated_deformable_im2col_cpu

src/lib/models/networks/DCNv2/src/cpu/dcn_v2_im2col_cpu.cpp:331

↓ 2 callersFunctionobject_pose_decode

( heat, kps, wh=None, kps_displacement_std=None, obj_scale=None, obj_scale_uncertainty=None, reg=None,

src/lib/models/decode.py:72

↓ 2 callersMethodparse_example

Parses image and label from a tf.Example proto. Args: example: A tf.Example proto. Returns: A tuple of image and its label.

data/objectron/dataset/parser.py:34

↓ 2 callersMethodreset

src/tools/objectron_eval/eval_video_official.py:269

↓ 2 callersMethodreset

src/lib/utils/tracker_baseline.py:51

↓ 2 callersFunctionrotation_y_matrix

src/lib/datasets/dataset_combined.py:33

↓ 2 callersMethodrun_epoch

(self, phase, epoch, data_loader)

src/lib/trains/base_trainer.py:55

↓ 2 callersMethodsample

Samples a 3D point uniformly inside this box.

data/objectron/dataset/box.py:181

↓ 2 callersMethodsave

(dict, var, name)

src/tools/objectron_eval/eval_video_official.py:1543

↓ 2 callersMethodsave_all_imgs_eval

(self, src_path, path='./cache/debug/', video_layout=False)

src/lib/utils/debugger.py:361

↓ 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:29

↓ 2 callersMethodshow_all_imgs

(self, pause=False, time=0)

src/lib/utils/debugger.py:335

↓ 2 callersMethodstats_save

(self, report_file)

src/tools/objectron_eval/eval_video_official.py:1541

↓ 2 callersMethodupdate

(self, data_json)

src/tools/objectron_eval/group_report_new.py:147

↓ 2 callersMethodwrite_report

Writes a report of the evaluation.

src/tools/objectron_eval/eval_video_official.py:1450

↓ 1 callersFunctionCHECK_EQ

src/tools/objectron_eval/eval_video_official.py:99

↓ 1 callersFunctionCHECK_EQ

src/tools/objectron_eval/eval_image_official.py:101

↓ 1 callersMethodLift2DTo3D

(self, projection_matrix, estimated_box, height, width, epnp_alpha_=epnp_alpha_default)

src/tools/objectron_eval/eval_video_official.py:1158

↓ 1 callersMethodLift2DTo3D

(self, projection_matrix, estimated_box, height, width, epnp_alpha_=epnp_alpha_default)

src/tools/objectron_eval/eval_image_official.py:805

↓ 1 callersMethod__init__

( self, opt, model, optimizer=None)

src/lib/trains/base_trainer.py:35

↓ 1 callersMethod__init__

src/lib/trains/object_pose.py:23

↓ 1 callersMethod__init__

(self, input_channels, hidden_channels, kernel_size, step=1, effective_step=[1])

src/lib/models/networks/convGRU.py:57

↓ 1 callersMethod_get_additional_inputs

Render input heatmap from previous trackings.

src/lib/detectors/base_detector.py:150

↓ 1 callersMethod_get_deconv_cfg

(self, deconv_kernel, index)

src/lib/models/networks/msra_resnet.py:195

↓ 1 callersMethod_get_deconv_cfg

(self, deconv_kernel, index)

src/lib/models/networks/resnet_dcn.py:200

↓ 1 callersMethod_get_losses

src/lib/trains/base_trainer.py:151

↓ 1 callersMethod_get_rotated_box

Rotate a box along its vertical axis. Args: box: Input box. angle: Rotation angle in rad. Returns: A rot

src/tools/objectron_eval/eval_image_official.py:721

↓ 1 callersMethod_is_visible

Determines if a 2D point is visible.

data/objectron/dataset/eval.py:465

↓ 1 callersMethod_is_visible

Determines if a 2D point is visible.

src/tools/objectron_eval/eval_video_official.py:1537

↓ 1 callersMethod_is_visible

Determines if a 2D point is visible.

src/tools/objectron_eval/eval_image_official.py:1181

↓ 1 callersMethod_is_visible

Determines if a 2D point is visible.

src/tools/objectron_eval/objectron/dataset/eval.py:464

↓ 1 callersMethod_make_deconv_layer

(self, num_layers, num_filters, num_kernels)

src/lib/models/networks/msra_resnet.py:208

↓ 1 callersMethod_make_deconv_layer

(self, num_layers, num_filters, num_kernels)

src/lib/models/networks/resnet_dcn.py:213

↓ 1 callersMethod_normalize_image

Normalizes pixels of an image from [0, 1] to [-1, 1].

data/objectron/dataset/parser.py:105

↓ 1 callersFunction_reg_loss

L1 regression loss Arguments: regr (batch x max_objects x dim) gt_regr (batch x max_objects x dim) mask (batch x max_ob

src/lib/models/losses.py:108

↓ 1 callersFunctionbilinear_interp_cpu

src/lib/models/networks/DCNv2/src/cpu/dcn_v2_psroi_pooling_cpu.cpp:34

↓ 1 callersFunctionbounding_box

src/lib/datasets/dataset_combined.py:40

↓ 1 callersFunctioncheck_gradient_dconv

src/lib/models/networks/DCNv2/testcpu.py:69

↓ 1 callersFunctioncheck_gradient_dconv

src/lib/models/networks/DCNv2/testcuda.py:69

↓ 1 callersFunctioncheck_gradient_dpooling

src/lib/models/networks/DCNv2/testcpu.py:134

↓ 1 callersFunctioncheck_gradient_dpooling

src/lib/models/networks/DCNv2/testcuda.py:134

↓ 1 callersFunctioncheck_pooling_zero_offset

src/lib/models/networks/DCNv2/testcpu.py:100

↓ 1 callersFunctioncheck_pooling_zero_offset

src/lib/models/networks/DCNv2/testcuda.py:100

↓ 1 callersFunctioncheck_zero_offset

src/lib/models/networks/DCNv2/testcpu.py:32

↓ 1 callersFunctioncheck_zero_offset

src/lib/models/networks/DCNv2/testcuda.py:32

↓ 1 callersFunctioncolor_aug

(data_rng, image, eig_val, eig_vec)

src/lib/utils/image.py:269

↓ 1 callersMethodcompute_ap

Calculates the AP given the recall and precision array. The reference implementation is from Pascal VOC 2012 eval script. First we filter the

data/objectron/dataset/metrics.py:50

↓ 1 callersMethodcompute_ap

Calculates the AP given the recall and precision array. The reference implementation is from Pascal VOC 2012 eval script. First we fi

src/tools/objectron_eval/objectron/dataset/metrics.py:50

↓ 1 callersMethodcompute_ap

Calculates the AP given the recall and precision array. The reference implementation is from Pascal VOC 2012 eval script. First we fi

src/tools/objectron_eval/objectron/dataset/metrics_nvidia.py:65

↓ 1 callersMethodcompute_ray

Computes a ray from camera to box centroid in box frame. For vertex in camera frame V^c, and object unit frame V^o, we have R * Vc + T = S

data/objectron/dataset/eval.py:212

↓ 1 callersMethodcompute_ray

Computes a ray from camera to box centroid in box frame. For vertex in camera frame V^c, and object unit frame V^o, we have R * Vc

src/tools/objectron_eval/eval_video_official.py:1217

← previous next →101–200 of 615, ranked by callers