Functions — github.com/ZhouYuxuanYX/BlockGCN

CodeHub MCPcopy Create free account

hub / github.com/ZhouYuxuanYX/BlockGCN / functions

Functions149 in github.com/ZhouYuxuanYX/BlockGCN

⨍ Functions 149◇ Types & classes 16

↓ 27 callersMethodprint_log

(self, str, print_time=True)

↓ 8 callersMethodprint_log

(self, str, print_time=True)

torchlight/torchlight/util.py:119

↓ 7 callersMethod__init__

model/BlockGCN.py:325

↓ 7 callersFunctionedge2mat

(link, num_node)

graph/tools.py:10

↓ 7 callersFunctionnormalize_digraph

graph/tools.py:27

↓ 6 callersFunctionbn_init

model/BlockGCN.py:38

↓ 4 callersFunctionconv_init

model/BlockGCN.py:31

↓ 4 callersMethodtop_k

(self, score, top_k)

feeders/feeder_ntu.py:115

↓ 3 callersMethodeval

(self, epoch, save_score=False, loader_name=['test'], wrong_file=None, result_file=None)

↓ 3 callersFunctionimport_class

↓ 3 callersMethodsplit_time

↓ 2 callersMethodL2_norm

model/BlockGCN.py:241

↓ 2 callersFunctionema_update

(source, target, decay=0.99, start_itr=20, itr=None)

↓ 2 callersFunctionget_one_actor_points

Get joints and colors for only one actor. For joints, each frame contains 75 X-Y-Z coordinates. For colors, each frame contains 25 x 2 (X

data/ntu/get_raw_denoised_data.py:223

↓ 2 callersFunctionget_one_actor_points

Get joints and colors for only one actor. For joints, each frame contains 75 X-Y-Z coordinates. For colors, each frame contains 25 x 2 (X

data/ntu120/get_raw_denoised_data.py:223

↓ 2 callersFunctionk_adjacency

(A, k, with_self=False, self_factor=1)

graph/tools.py:52

↓ 2 callersFunctionone_hot_vector

data/ntu/seq_transformation.py:130

↓ 2 callersFunctionone_hot_vector

data/ntu120/seq_transformation.py:130

↓ 2 callersMethodrand_view_transform

(self,X, agx, agy, s)

feeders/feeder_ucla.py:66

↓ 2 callersMethodrecord_time

↓ 2 callersMethodrecord_time

torchlight/torchlight/util.py:137

↓ 1 callersMethodL2_norm

model/BlockGCN.py:330

↓ 1 callersMethod__init__

↓ 1 callersMethod__init__

(self, work_dir, save_log=True, print_log=True)

torchlight/torchlight/util.py:20

↓ 1 callersFunction_rot

feeders/tools.py:151

↓ 1 callersMethodadjust_learning_rate

↓ 1 callersFunctionalign_frames

Align all sequences with the same frame length.

data/ntu/seq_transformation.py:109

↓ 1 callersFunctionalign_frames

Align all sequences with the same frame length.

data/ntu120/seq_transformation.py:109

↓ 1 callersFunctionauto_pading

(data_numpy, size, random_pad=False)

feeders/tools.py:65

↓ 1 callersFunctiondenoising_bodies_data

Denoising data based on some heuristic methods, not necessarily correct for all samples. Return: denoised_bodies_data (list): tuple: (

data/ntu/get_raw_denoised_data.py:174

↓ 1 callersFunctiondenoising_bodies_data

Denoising data based on some heuristic methods, not necessarily correct for all samples. Return: denoised_bodies_data (list): tuple: (

data/ntu120/get_raw_denoised_data.py:174

↓ 1 callersFunctiondenoising_by_length

Denoising data based on the frame length for each bodyID. Filter out the bodyID which length is less or equal than the predefined threshold.

data/ntu/get_raw_denoised_data.py:71

↓ 1 callersFunctiondenoising_by_length

Denoising data based on the frame length for each bodyID. Filter out the bodyID which length is less or equal than the predefined threshold.

data/ntu120/get_raw_denoised_data.py:71

↓ 1 callersFunctiondenoising_by_spread

Denoising data based on the spread of Y value and X value. Filter out the bodyID which the ratio of noisy frames is higher than the predefine

data/ntu/get_raw_denoised_data.py:108

↓ 1 callersFunctiondenoising_by_spread

Denoising data based on the spread of Y value and X value. Filter out the bodyID which the ratio of noisy frames is higher than the predefine

data/ntu120/get_raw_denoised_data.py:108

↓ 1 callersMethodget_adjacency_matrix

(self, labeling_mode=None)

graph/ucla.py:27

↓ 1 callersMethodget_adjacency_matrix

(self, labeling_mode=None)

graph/ntu_rgb_d.py:52

↓ 1 callersFunctionget_bodies_info

data/ntu/get_raw_denoised_data.py:281

↓ 1 callersFunctionget_bodies_info

data/ntu120/get_raw_denoised_data.py:281

↓ 1 callersFunctionget_indices

(performer, camera, evaluation='CS')

data/ntu/seq_transformation.py:192

↓ 1 callersFunctionget_indices

(performer, setup, evaluation='CSub')

data/ntu120/seq_transformation.py:192

↓ 1 callersMethodget_mean_map

feeders/feeder_ucla.py:54

↓ 1 callersMethodget_mean_map

feeders/feeder_ntu.py:63

↓ 1 callersFunctionget_parser

↓ 1 callersFunctionget_raw_bodies_data

Get raw bodies data from a skeleton sequence. Each body's data is a dict that contains the following keys: - joints: raw 3D joints pos

data/ntu/get_raw_skes_data.py:10

↓ 1 callersFunctionget_raw_bodies_data

Get raw bodies data from a skeleton sequence. Each body's data is a dict that contains the following keys: - joints: raw 3D joints pos

data/ntu120/get_raw_skes_data.py:10

↓ 1 callersFunctionget_raw_denoised_data

Get denoised data (joints positions and color locations) from raw skeleton sequences. For each frame of a skeleton sequence, an actor's 3D p

data/ntu/get_raw_denoised_data.py:367

↓ 1 callersFunctionget_raw_denoised_data

Get denoised data (joints positions and color locations) from raw skeleton sequences. For each frame of a skeleton sequence, an actor's 3D p

data/ntu120/get_raw_denoised_data.py:367

↓ 1 callersFunctionget_raw_skes_data

data/ntu/get_raw_skes_data.py:94

↓ 1 callersFunctionget_raw_skes_data

data/ntu120/get_raw_skes_data.py:96

↓ 1 callersFunctionget_two_actors_points

Get the first and second actor's joints positions and colors locations. # Arguments: bodies_data (dict): 3 key-value pairs: 'name',

data/ntu/get_raw_denoised_data.py:290

↓ 1 callersFunctionget_two_actors_points

Get the first and second actor's joints positions and colors locations. # Arguments: bodies_data (dict): 3 key-value pairs: 'name',

data/ntu120/get_raw_denoised_data.py:290

↓ 1 callersFunctionget_valid_frames_by_spread

Find the valid (or reasonable) frames (index) based on the spread of X and Y. :param points: joints or colors

data/ntu/get_raw_denoised_data.py:92

↓ 1 callersFunctionget_valid_frames_by_spread

Find the valid (or reasonable) frames (index) based on the spread of X and Y. :param points: joints or colors

data/ntu120/get_raw_denoised_data.py:92

↓ 1 callersFunctionimport_class

model/BlockGCN.py:13

↓ 1 callersFunctionimport_class

torchlight/torchlight/util.py:177

↓ 1 callersFunctioninit_seed

↓ 1 callersMethodload_data

↓ 1 callersMethodload_data

feeders/feeder_ucla.py:42

↓ 1 callersMethodload_data

feeders/feeder_ntu.py:47

↓ 1 callersMethodload_model

↓ 1 callersMethodload_optimizer

↓ 1 callersMethodlog

(self, *args, **kwargs)

torchlight/torchlight/util.py:30

↓ 1 callersFunctionremove_missing_frames

Cut off missing frames which all joints positions are 0s For the sequence with 2 actors' data, also record the number of missing frames for

data/ntu/get_raw_denoised_data.py:238

↓ 1 callersFunctionremove_missing_frames

Cut off missing frames which all joints positions are 0s For the sequence with 2 actors' data, also record the number of missing frames for

data/ntu120/get_raw_denoised_data.py:238

↓ 1 callersFunctionremove_nan_frames

(ske_name, ske_joints, nan_logger)

data/ntu/seq_transformation.py:31

↓ 1 callersFunctionremove_nan_frames

(ske_name, ske_joints, nan_logger)

data/ntu120/seq_transformation.py:31

↓ 1 callersMethodsave_arg

↓ 1 callersFunctionseq_translation

data/ntu/seq_transformation.py:44

↓ 1 callersFunctionseq_translation

data/ntu120/seq_transformation.py:44

↓ 1 callersFunctionsplit_dataset

(skes_joints, label, performer, camera, evaluation, save_path)

data/ntu/seq_transformation.py:156

↓ 1 callersFunctionsplit_dataset

(skes_joints, label, performer, setup, evaluation, save_path)

data/ntu120/seq_transformation.py:156

↓ 1 callersMethodsplit_time

torchlight/torchlight/util.py:141

↓ 1 callersMethodstart

↓ 1 callersMethodtrain

(self, epoch, save_model=False)

(self, parser, namespace, values, option_string=None)

torchlight/torchlight/util.py:192

Method__getitem__

feeders/feeder_ucla.py:76

Method__getitem__

feeders/feeder_ntu.py:75

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

model/BlockGCN.py:58

(self, in_channels, out_channels, kernel_size=5, stride=1)

model/BlockGCN.py:77

(self, in_channels, out_channels, kernel_size=3,

model/BlockGCN.py:93

(self, in_channels, out_channels, A, adaptive=True, alpha=False)

model/BlockGCN.py:171

(self, in_channels, out_channels, A, stride=1, residual=True, adaptive=True, kernel_size=5, dilations=[1,2], n

model/BlockGCN.py:276

(self, out_dim)

model/BlockGCN.py:303

(self, num_class=60, num_point=25, num_person=2, graph=None, graph_args=dict(), in_channels=3,

model/BlockGCN.py:348

(self, labeling_mode='spatial', scale=1)

graph/ucla.py:19

(self, labeling_mode='spatial', scale=1)

graph/ntu_rgb_d.py:34

(self, data_path, label_path, repeat=1, random_choose=False, random_shift=False, random_move=False,

feeders/feeder_ucla.py:10

:param data_path: :param label_path: :param split: training set or test set :param random_choose: If true, random

feeders/feeder_ntu.py:9

(self, option_strings, dest, nargs=None, **kwargs)

torchlight/torchlight/util.py:187

feeders/feeder_ucla.py:63

feeders/feeder_ntu.py:72

feeders/feeder_ucla.py:60

feeders/feeder_ntu.py:69

Function_import_class_0

torchlight/torchlight/util.py:169

Methodcheck_time

torchlight/torchlight/util.py:134

Functionconv_branch_init

(conv, branches)

model/BlockGCN.py:21

Methodcount_parameters

Functiondenoising_by_motion

Filter out the bodyID which motion is out of the range of predefined interval

data/ntu/get_raw_denoised_data.py:149

next →1–100 of 149, ranked by callers