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

Assertion error #6

Open jay1999ke opened 5 years ago

jay1999ke commented 5 years ago

The following assertion error occurs when tested on h36m dataset:

Run command: python predict_3dpose_mdm.py --test True --load 4679232 --load_dir ../Models/mdm_5/

error callback: AssertionError Traceback (most recent call last) D:\MLWorkspace\Pose estimations\Generating-Multiple-Hypotheses-for-3D-Human-Pose-Estimation-with-Mixture-Density-Network\src\predict_3dpose_mdm.py in 647 if name == "main": 648 --> 649 tf.app.run()

~\Anaconda3\lib\site-packages\tensorflow\python\platform\app.py in run(main, argv) 38 main = main or _sys.modules['main'].main 39 ---> 40 _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)

~\Anaconda3\lib\site-packages\absl\app.py in run(main, argv, flags_parser) 298 callback() 299 try: --> 300 _run_main(main, args) 301 except UsageError as error: 302 usage(shorthelp=True, detailed_error=error, exitcode=error.exitcode)

~\Anaconda3\lib\site-packages\absl\app.py in _run_main(main, argv) 249 sys.exit(retval) 250 else: --> 251 sys.exit(main(argv)) 252 253

D:\MLWorkspace\Pose estimations\Generating-Multiple-Hypotheses-for-3D-Human-Pose-Estimation-with-Mixture-Density-Network\src\predict_3dposemdm.py in main() 641 sample() 642 elif FLAGS.test: --> 643 test() 644 else: 645 train()

D:\MLWorkspace\Pose estimations\Generating-Multiple-Hypotheses-for-3D-Human-Pose-Estimation-with-Mixture-Density-Network\src\predict_3dpose_mdm.py in test() 425 # Read stacked hourglass 2D predictions if use_sh, otherwise use groundtruth 2D projections 426 if FLAGS.use_sh: --> 427 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) 428 else: 429 train_set_2d, test_set_2d, data_mean_2d, data_std_2d, dim_to_ignore_2d, dim_to_use_2d = data_utils.create_2d_data( actions, FLAGS.data_dir, rcams )

D:\MLWorkspace\Pose estimations\Generating-Multiple-Hypotheses-for-3D-Human-Pose-Estimation-with-Mixture-Density-Network\src\data_utils.py in read_2d_predictions(actions, data_dir) 378 """ 379 --> 380 train_set = load_stacked_hourglass( data_dir, TRAIN_SUBJECTS, actions) 381 test_set = load_stacked_hourglass( data_dir, TEST_SUBJECTS, actions) 382

D:\MLWorkspace\Pose estimations\Generating-Multiple-Hypotheses-for-3D-Human-Pose-Estimation-with-Mixture-Density-Network\src\data_utils.py in load_stacked_hourglass(data_dir, subjects, actions) 185 assert loaded_seqs == 7, "Expecting 7 sequences, found {0} instead. S:{1} {2}".format(loaded_seqs, subj, action ) 186 else: --> 187 assert loaded_seqs == 8, "Expecting 8 sequences, found {0} instead. S:{1} {2}".format(loaded_seqs, subj, action ) 188 189 return data

AssertionError: Expecting 8 sequences, found 0 instead. S:1 Directions

chaneyddtt commented 4 years ago

Hi @jay1999ke, Seems that you can not load the data properly. Can you double check that you have downloaded the 2d joints detections and put them in the correct folder?