search

chaneyddtt / Generating-Multiple-Hypotheses-for-3D-Human-Pose-Estimation-with-Mixture-Density-Network

Code for our CVPR2019 paper: Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network
MIT License
97 stars 9 forks source link

bugs #13

Closed cuge1995 closed 3 years ago

cuge1995 commented 3 years ago

src/cameras.py", line 118, in name = "".join( [chr(item) for item in name] ) TypeError: only integer scalar arrays can be converted to a scalar index

chaneyddtt commented 3 years ago

Hi, Can you give more details of your error because I can not reproduce the error you show. Thanks.

cuge1995 commented 3 years ago

this is solved by

name = "".join( [chr(int(item)) for item in name] )
cuge1995 commented 3 years ago

but another bug occur

File "predict_3dpose_mdm.py", line 173, in train
    train_set_2d, test_set_2d, data_mean_2d, data_std_2d, dim_to_ignore_2d, dim_to_use_2d = data_utils.read_2d_predictions(actions, FLAGS.data_dir)
  File "/home/cuge/Documents/money/human3d/src/data_utils.py", line 381, in read_2d_predictions
    train_set = load_stacked_hourglass( data_dir, TRAIN_SUBJECTS, actions)
  File "/home/cuge/Documents/money/human3d/src/data_utils.py", line 188, in load_stacked_hourglass
    assert loaded_seqs == 8, "Expecting 8 sequences, found {0} instead. S:{1} {2}".format(loaded_seqs, subj, action )
AssertionError: Expecting 8 sequences, found 0 instead. S:1 Directions
cuge1995 commented 3 years ago

solved by replace

'StackedHourglass/{0}*.h5'       'StackedHourglass***240/{0}*.h5'