Functions — github.com/MaureenZOU/TSAM

hub / github.com/MaureenZOU/TSAM / functions

Functions693 in github.com/MaureenZOU/TSAM

⨍ Functions 693◇ Types & classes 158

↓ 216 callersMethodappend

(self, file_)

src/utils/readers.py:119

↓ 26 callersMethodsave

(self,file='index')

libs/PerceptualSimilarity/util/html.py:47

↓ 22 callersFunctionget_everything_under

(root_dir, pattern='*', only_dirs=False, only_files=False)

src/utils/util.py:235

↓ 14 callersFunctionmake_dirs

(dir_name)

src/utils/util.py:38

↓ 12 callersMethod__init__

( self, in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bia

src/model/blocks.py:278

↓ 12 callersMethod__init__

(self)

src/model/loss_module.py:300

↓ 11 callersMethod__init__

(self, dir_name, read=True, max_length=None, sample_period=1, evaluate_image=False)

src/utils/readers.py:95

↓ 11 callersMethod__init__

(self)

src/model/loss.py:292

↓ 9 callersFunction_resnet

(arch, block, layers, pretrained, progress, **kwargs)

src/model/tsm/resnet.py:229

↓ 8 callersMethodforward

(self, in0, in1)

libs/PerceptualSimilarity/models/networks_basic.py:229

↓ 8 callersFunctionget_instance

(module, name, config, *args, **kwargs)

src/train.py:19

↓ 8 callersFunctionget_instance

(module, name, config, *args, **kwargs)

src/test.py:19

↓ 8 callersMethodinitialize

INPUTS model - ['net-lin'] for linearly calibrated network ['net'] for off-the-shelf network

libs/PerceptualSimilarity/models/dist_model.py:24

↓ 8 callersFunctionmake_block_temporal

(stage, this_segment)

src/model/tsm/temporal_shift.py:271

↓ 8 callersMethodworker

(self, flow)

src/data_loader/transform_flow.py:48

↓ 6 callersMethodbackward

(ctx, grad_output)

src/model/tsm_utils.py:24

↓ 6 callersFunctionget_edge

(tensor)

src/utils/edge.py:15

↓ 6 callersFunctionget_i3d_activations

Get features from i3d model and flatten them to 1d feature, valid target endpoints are defined in InceptionI3d.VALID_ENDPOINTS VALID_END

src/evaluate.py:344

↓ 6 callersFunctionget_landmarks_contour

(image, landmarks_predictor_path=DEFAULT_PATH)

src/utils/face.py:87

↓ 6 callersFunctioninterpolate

(x, scale_factor=2, mode='nearest')

src/model/tsm/module.py:45

↓ 6 callersFunctionread_dirnames_under_root

(root_dir, skip_list=[])

src/utils/util.py:59

↓ 6 callersMethodread_files

(self, filenames)

src/utils/readers.py:125

↓ 5 callersMethod__init__

(self, conv_type, dconv_type=None)

src/model/modules.py:18

↓ 5 callersMethod__init__

(self, pnet_type='vgg', pnet_rand=False, use_gpu=True)

libs/PerceptualSimilarity/models/networks_basic.py:18

↓ 5 callersMethodforward

Pred and target are Variables. If normalize is on, assumes the images are between [0,1] and then scales thembetween [-1, 1] I

libs/PerceptualSimilarity/__init__.py:16

↓ 5 callersFunctionmake_dir_under_root

(root_dir, name)

src/utils/util.py:47

↓ 5 callersMethodset_step

(self, step, mode='train')

src/utils/visualization.py:28

↓ 4 callersMethod__init__

(self, backbone, nc_in, nc_out, nf, use_bias, norm, conv_by, conv_type, use_skip_connection: bool = False, use

src/model/networks.py:14

↓ 4 callersMethod_make_layer

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

src/model/tsm/resnet.py:187

↓ 4 callersMethodadd_images

(self, ims, txts, links, width=400)

libs/PerceptualSimilarity/util/html.py:35

↓ 4 callersMethodforward_pair

(self,in1,in2,retPerLayer=False)

libs/PerceptualSimilarity/models/dist_model.py:101

↓ 4 callersFunctionget_every

(d)

src/scripts/mask_scripts/apply_mask.py:30

↓ 4 callersFunctionget_masked_ratio

Calculate the masked ratio. mask: Expected a binary PIL image, where 0 and 1 represent masked(invalid) and valid pixel values.

src/utils/mask_generators.py:210

↓ 4 callersFunctionget_video_masks_by_moving_random_stroke

Get video masks by random strokes which move randomly between each frame, including the whole stroke and its control points Parameters

src/utils/mask_generators.py:6

↓ 4 callersMethodsave_files

(self, output_dir=None)

src/utils/readers.py:134

↓ 4 callersFunctionwarp_optical_flow

Modified from https://github.com/NVlabs/PWC-Net/blob/fc6ebf9a70a7387164df09a3a2070ba16f9c1ede/PyTorch/models/PWCNet.py # NOQA warp an im2 ba

src/utils/flow_utils.py:6

↓ 4 callersFunctionzoom_to_res

(img,res=256,order=0,axis=0)

libs/PerceptualSimilarity/util/visualizer.py:11

↓ 3 callersMethod__init__

( self, rids: RootInputDirectories, rods: RootOutputDirectories, args: dict,

src/data_loader/dataset.py:35

↓ 3 callersMethod__init__

(self, net, n_segment)

src/model/tsm/temporal_shift.py:234

↓ 3 callersMethod__init__

(self, requires_grad=False, pretrained=True)

libs/PerceptualSimilarity/models/pretrained_networks.py:97

↓ 3 callersMethod_process_data

(self, data, validation=False)

src/trainer/trainer.py:352

↓ 3 callersMethod_unpack_data

(self, data_input, model_output)

src/trainer/trainer.py:401

↓ 3 callersMethod_write_images

( self, inputs, outputs, targets, masks, output_edges=None, target_edges=None, model_o

src/trainer/trainer.py:264

↓ 3 callersMethodcompute_pad

(self, dim, s)

src/model/i3d.py:10

↓ 3 callersMethodcompute_pad

(self, dim, s)

src/model/i3d.py:69

↓ 3 callersFunctionconv1x1

1x1 convolution

src/model/tsm/resnet.py:39

↓ 3 callersFunctionconv3x3

3x3 convolution with padding

src/model/tsm/resnet.py:33

↓ 3 callersFunctioncreate_random_shape_with_random_motion

(video_length, imageHeight=240, imageWidth=432)

src/utils/stationary_mask.py:30

↓ 3 callersFunctionevaluate_video_error

( result_images, gt_images, masks, flownet_checkpoint_path, evaluate_warping_error=False, printlog

src/evaluate.py:168

↓ 3 callersMethodforward

(self, x, flows)

src/model/tsm/module.py:23

↓ 3 callersMethodforward

(self)

libs/PerceptualSimilarity/perceptual_loss.py:37

↓ 3 callersMethodforward

Function computes the distance between image patches in0 and in1 INPUTS in0, in1 - torch.Tensor object of shape Nx3xXxY - image p

libs/PerceptualSimilarity/models/dist_model.py:107

↓ 3 callersFunctionget_fid_score

Given two distribution of features, compute the FID score between them

src/evaluate.py:379

↓ 3 callersMethodget_samples

(self, start, end)

src/utils/readers.py:472

↓ 3 callersMethodget_samples

(self, start, end)

src/utils/readers.py:492

↓ 3 callersFunctioninit_i3d_model

()

src/evaluate.py:38

↓ 3 callersMethodload_data

()

libs/PerceptualSimilarity/data/base_data_loader.py:9

↓ 3 callersMethodpostprocess

(self, masked_imgs, masks, c11)

src/model/networks.py:85

↓ 3 callersMethodset_files

(self, files)

src/utils/readers.py:122

↓ 3 callersMethodshow

(self)

src/utils/screen.py:16

↓ 3 callersMethodtrain

Override the default train() to freeze the BN parameters :return:

src/model/tsm/models.py:180

↓ 3 callersMethodwrite_files_to_video

(self, output_filename, fps=DEFAULT_FPS, frame_num_when_repeat_list=[1])

src/utils/readers.py:481

↓ 2 callersFunctionLaguerre_Gauss_Circular_Harmonic_1_0

(size, sigma)

libs/video_quality/reco.py:46

↓ 2 callersFunctionLaguerre_Gauss_Circular_Harmonic_3_0

(size, sigma)

libs/video_quality/reco.py:36

↓ 2 callersMethod__init__

Initializes Unit3D module.

src/model/i3d.py:37

↓ 2 callersMethod__init__

(self, df=32)

src/model/completion_model.py:82

↓ 2 callersMethod__init__

(self, block, layers, num_classes=1000, zero_init_residual=False, groups=1, width_per_group=6

src/model/tsm/resnet.py:134

↓ 2 callersMethod_cut_to_align

Cut the boarder by 1 frame(temporal)/row(height)/col(width) such that dimensions of x and y could be the same.

src/model/completion_model.py:36

↓ 2 callersFunction_decide_patch_num

(box_width, patch_size)

src/utils/util.py:112

↓ 2 callersMethod_eval_metrics

(self, output, target)

src/trainer/trainer.py:304

↓ 2 callersMethod_get_mask_name

(self, index)

src/data_loader/dataset.py:170

↓ 2 callersMethod_get_non_gan_loss

(self, non_gan_loss)

src/trainer/trainer.py:411

↓ 2 callersMethod_process_data

(self, data, validation=False)

src/trainer/inference.py:344

↓ 2 callersMethod_unpack_data

(self, data_input, model_output)

src/trainer/inference.py:393

↓ 2 callersMethod_write_images

( self, inputs, outputs, targets, masks, output_edges=None, target_edges=None, model_o

src/trainer/inference.py:256

↓ 2 callersMethodadd_entry

(self, entry)

src/utils/logger.py:13

↓ 2 callersMethodadd_header

(self, str)

libs/PerceptualSimilarity/util/html.py:27

↓ 2 callersFunctionblock_view

Provide a 2D block view to 2D array. No error checking made. Therefore meaningful (as implemented) only for blocks strictly compatible with th

libs/video_quality/ssim.py:27

↓ 2 callersFunctioncluster_by_masked_area

(root_dir, args)

src/scripts/mask_scripts/gen_masks_davis.py:182

↓ 2 callersFunctioncluster_by_masked_area

(root_dir, args)

src/scripts/mask_scripts/gen_masks.py:182

↓ 2 callersMethodconcat_feature

(self, ca, cb)

src/model/modules.py:133

↓ 2 callersFunctiondecide_nStroke

(args)

src/scripts/mask_scripts/gen_masks_davis.py:217

↓ 2 callersFunctiondecide_nStroke

(args)

src/scripts/mask_scripts/gen_masks.py:217

↓ 2 callersFunctiondraw_mask_by_control_points

(mask, Xs, Ys, brushWidth, fill=255)

src/utils/mask_generators.py:178

↓ 2 callersFunctioneco

(img)

libs/video_quality/reco.py:73

↓ 2 callersFunctionerase_mask_boarder

(mask, gap)

src/scripts/mask_scripts/gen_masks_davis.py:153

↓ 2 callersFunctionerase_mask_boarder

(mask, gap)

src/scripts/mask_scripts/gen_masks.py:153

↓ 2 callersFunctionestimate_aggd_params

(x)

libs/video_quality/niqe.py:89

↓ 2 callersFunctionevaluate_fid_score

(root_gt_dir, root_result_dir, result_postfix)

src/evaluate.py:278

↓ 2 callersMethodevaluate_test_set

(self, output_root_dir=None, epoch=None, log=None)

src/trainer/inference.py:440

↓ 2 callersMethodevaluate_test_set

(self, output_root_dir=None, epoch=None, log=None)

src/trainer/trainer.py:526

↓ 2 callersMethodfill_fix_offset

(more_fix_crop, image_w, image_h, crop_w, crop_h)

src/data_loader/transform_flow.py:246

↓ 2 callersMethodfill_fix_offset

(more_fix_crop, image_w, image_h, crop_w, crop_h)

src/data_loader/transform.py:184

↓ 2 callersMethodflip_flow

(self, flow)

src/data_loader/transform_flow.py:76

↓ 2 callersFunctionflow_to_grid

(flow)

src/utils/visual_helper.py:138

↓ 2 callersFunctionflow_to_image

Convert flow into middlebury color code image :param flow: optical flow map :return: optical flow image in middlebury color

src/utils/flow_utils.py:47

↓ 2 callersMethodget_bboxeses

(self)

src/utils/readers.py:251

↓ 2 callersFunctionget_every

(d)

src/scripts/reorder.py:25

↓ 2 callersFunctionget_every

(d)

src/scripts/leave_32frames.py:26

↓ 2 callersMethodget_image_dir

(self)

libs/PerceptualSimilarity/util/html.py:24

next →1–100 of 693, ranked by callers