Functions — github.com/charigyang/motiongrouping

CodeHub MCPcopy Create free account

hub / github.com/charigyang/motiongrouping / functions

Functions126 in github.com/charigyang/motiongrouping

⨍ Functions 126◇ Types & classes 32

↓ 6 callersMethod__init__

(self, hidden_dim=128, input_dim=192+128)

raft/core/update.py:17

↓ 4 callersMethod__init__

(self, aug_params=None, root='datasets/HD1k')

raft/core/datasets.py:181

↓ 4 callersFunctionload_image

(imfile, resolution=None)

raft/predict.py:39

↓ 4 callersMethodupdate

(self, val, n=1)

tools/MoCA_eval.py:84

↓ 3 callersMethod__init__

(self, output_dim=128, norm_fn='batch', dropout=0.0)

raft/core/extractor.py:119

↓ 3 callersMethod_make_layer

(self, dim, stride=1)

raft/core/extractor.py:159

↓ 3 callersMethod_make_layer

(self, dim, stride=1)

raft/core/extractor.py:235

↓ 3 callersFunctioniou

(masks, gt, thres=0.5)

src/utils.py:100

↓ 3 callersFunctionreadFlow

(sample_dir, resolution, to_rgb)

↓ 2 callersMethod__init__

Builds the Slot Attention module. Args: iters: Number of iterations. num_slots: Number of slots. encoder_d

src/model.py:61

↓ 2 callersFunctioncoords_grid

(batch, ht, wd)

raft/core/utils/utils.py:74

↓ 2 callersFunctioneval

(val_loader, model, device, moca, use_flow, it, resultsPath=None, writer=None, train=False)

↓ 2 callersFunctionreadRGB

(sample_dir, resolution)

↓ 2 callersFunctionreadSeg

↓ 1 callersMethod__init__

(self, sampler)

src/utils.py:170

↓ 1 callersMethod__iter__

src/utils.py:173

↓ 1 callersFunctionbb_intersection_over_union

tools/MoCA_eval.py:41

↓ 1 callersFunctionbb_intersection_over_union

src/utils.py:34

↓ 1 callersFunctionbilinear_sampler

Wrapper for grid_sample, uses pixel coordinates

raft/core/utils/utils.py:57

↓ 1 callersFunctionbuild_grid

↓ 1 callersMethodcolor_transform

Photometric augmentation

raft/core/utils/augmentor.py:36

↓ 1 callersMethodcolor_transform

(self, img1, img2)

raft/core/utils/augmentor.py:142

↓ 1 callersFunctioncombine

tools/SegTrack_clean.py:6

↓ 1 callersMethodcorr

raft/core/corr.py:53

↓ 1 callersMethoderaser_transform

Occlusion augmentation

raft/core/utils/augmentor.py:52

↓ 1 callersMethoderaser_transform

(self, img1, img2)

raft/core/utils/augmentor.py:148

↓ 1 callersFunctionfind_gt

tools/FBMS_clean.py:27

↓ 1 callersFunctionflow_uv_to_colors

Applies the flow color wheel to (possibly clipped) flow components u and v. According to the C++ source code of Daniel Scharstein Accord

raft/core/utils/flow_viz.py:70

↓ 1 callersMethodforward

Estimate optical flow between pair of frames

raft/core/raft.py:86

↓ 1 callersFunctionheuristic_fg_bg

tools/MoCA_eval.py:65

↓ 1 callersFunctionheuristic_fg_bg

src/utils.py:58

↓ 1 callersMethodinitialize_flow

Flow is represented as difference between two coordinate grids flow = coords1 - coords0

raft/core/raft.py:63

↓ 1 callersFunctionmain

tools/MoCA_eval.py:91

↓ 1 callersFunctionmain

↓ 1 callersFunctionmain

src/train.py:18

↓ 1 callersFunctionmake_colorwheel

Generates a color wheel for optical flow visualization as presented in: Baker et al. "A Database and Evaluation Methodology for Optical F

raft/core/utils/flow_viz.py:20

↓ 1 callersMethodmake_encoder

(self, in_channels, encoder_arch)

src/model.py:204

↓ 1 callersMethodpad

(self, *inputs)

raft/core/utils/utils.py:18

↓ 1 callersFunctionpredict

raft/predict.py:48

↓ 1 callersFunctionreadFlow

Read .flo file in Middlebury format

raft/core/utils/frame_utils.py:12

↓ 1 callersFunctionreadPFM

raft/core/utils/frame_utils.py:33

↓ 1 callersFunctionread_annotation

tools/MoCA_eval.py:11

↓ 1 callersFunctionread_flo

src/utils.py:149

↓ 1 callersFunctionrectangle_iou

src/utils.py:65

↓ 1 callersMethodreset

tools/MoCA_eval.py:78

↓ 1 callersMethodresize_sparse_flow_map

(self, flow, valid, fx=1.0, fy=1.0)

raft/core/utils/augmentor.py:161

↓ 1 callersFunctionspatial_broadcast

Broadcast slot features to a 2D grid and collapse slot dimension.

src/model.py:38

↓ 1 callersFunctionspatial_flatten

src/model.py:47

↓ 1 callersMethodspatial_transform

(self, img1, img2, flow)

raft/core/utils/augmentor.py:67

↓ 1 callersMethodspatial_transform

(self, img1, img2, flow, valid)

raft/core/utils/augmentor.py:195

↓ 1 callersFunctionunstack_and_split

Unstack batch dimension and split into channels and alpha mask.

src/model.py:51

↓ 1 callersFunctionupflow8

(flow, mode='bilinear')

raft/core/utils/utils.py:80

↓ 1 callersMethodupsample_flow

Upsample flow field [H/8, W/8, 2] -> [H, W, 2] using convex combination

raft/core/raft.py:72

↓ 1 callersFunctionwriteFlowFile

According to the matlab code of Deqing Sun and c++ source code of Daniel Scharstein Contact: dqsun@cs.brown.edu Contact: schar@middlebury

raft/predict.py:21

raft/core/corr.py:29

raft/core/corr.py:74

(self, img1, img2, flow)

raft/core/utils/augmentor.py:111

(self, img1, img2, flow, valid)

raft/core/utils/augmentor.py:236

Method__enter__

raft/core/raft.py:18

raft/core/raft.py:20

Method__getitem__

Method__getitem__

Method__getitem__

raft/core/datasets.py:34

tools/MoCA_eval.py:75

(self, *args, **kwargs)

src/utils.py:180

(self, data_dir, resolution, to_rgb=False, with_rgb=False, with_gt=True)

(self, data_dir, resolution, pair_list, val_seq, to_rgb=False, with_rgb=False)

Builds the soft position embedding layer. Args: hidden_size: Size of input feature dimension. resolution: Tuple of integers specifyin

src/model.py:23

Builds the Slot Attention-based Auto-encoder. Args: resolution: Tuple of integers specifying width and height of input image

src/model.py:148

(self, in_planes, planes, norm_fn='group', stride=1)

raft/core/extractor.py:7

(self, in_planes, planes, norm_fn='group', stride=1)

raft/core/extractor.py:61

(self, output_dim=128, norm_fn='batch', dropout=0.0)

raft/core/extractor.py:196

(self, aug_params=None, sparse=False)

raft/core/datasets.py:19

(self, aug_params=None, split='training', root='datasets/Sintel', dstype='clean')

raft/core/datasets.py:103

(self, aug_params=None, split='train', root='datasets/FlyingChairs_release/data')

raft/core/datasets.py:122

(self, aug_params=None, root='datasets/FlyingThings3D', dstype='frames_cleanpass')

raft/core/datasets.py:138

(self, aug_params=None, split='training', root='datasets/KITTI')

raft/core/datasets.py:162

(self, fmap1, fmap2, num_levels=4, radius=4)

raft/core/corr.py:13

(self, fmap1, fmap2, num_levels=4, radius=4)

raft/core/corr.py:64

(self, input_dim=128, hidden_dim=256)

raft/core/update.py:7

(self, hidden_dim=128, input_dim=192+128)

raft/core/update.py:34

raft/core/update.py:63

raft/core/update.py:80

(self, args, hidden_dim=96)

raft/core/update.py:100

(self, args, hidden_dim=128, input_dim=128)

raft/core/update.py:115

(self, enabled)

raft/core/raft.py:16

raft/core/raft.py:25

(self, crop_size, min_scale=-0.2, max_scale=0.5, do_flip=True)

raft/core/utils/augmentor.py:16

(self, crop_size, min_scale=-0.2, max_scale=0.5, do_flip=False)

raft/core/utils/augmentor.py:123

(self, dims, mode='sintel')

raft/core/utils/utils.py:9

src/utils.py:189

src/utils.py:186

raft/core/datasets.py:98

raft/core/datasets.py:93

Functionconvert_for_vis

(inp, use_flow=False)

src/utils.py:16

Functionensemble_hungarian_iou

(masks, gt, moca=False)

src/utils.py:106

Functionfetch_dataloader

Create the data loader for the corresponding trainign set

raft/core/datasets.py:199

Functionflow_to_image

Expects a two dimensional flow image of shape. Args: flow_uv (np.ndarray): Flow UV image of shape [H,W,2] clip_flow (float,

raft/core/utils/flow_viz.py:109

next →1–100 of 126, ranked by callers