search

Healthcare-Robotics / bodies-at-rest

Code + Data for CVPR 2020 oral paper "Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic Data."
Other
63 stars 8 forks source link

Error loading trained ConvNets #16

Closed YoloZyk closed 4 months ago

YoloZyk commented 5 months ago

Dear author: Thank you for this amazing work. I'm trying to reproduce this working but when I load the model in download_model.sh like below,

self.model = torch.load(FILEPATH_PREFIX + "/convnets/convnet_1_anglesDC_184000ct_128b_x1pm_tnh_clns20p_100e_2e-05lr.pt", map_location='cpu')
self.model2 = torch.load(FILEPATH_PREFIX + "/convnets/convnet_2_anglesDC_184000ct_128b_x1pm_0.5rtojtdpth_depthestin_angleadj_tnh_clns20p_100e_2e-05lr.pt", map_location='cpu')

I'm stuck on the following error.

Traceback (most recent call last):
  File "evaluate_synth.py", line 901, in <module>
    p.init_convnet_test()
  File "evaluate_synth.py", line 305, in init_convnet_test
    self.model = torch.load(FILEPATH_PREFIX + "/convnets/convnet_1_anglesDC_184000ct_128b_x1pm_tnh_clns20p_100e_2e-05lr.pt", map_location='cpu')
  File "/opt/conda/lib/python3.8/site-packages/torch/serialization.py", line 713, in load
    return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
  File "/opt/conda/lib/python3.8/site-packages/torch/serialization.py", line 930, in _legacy_load
    result = unpickler.load()
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xff in position 0: invalid start byte

I'm not sure if the model file provided is corrupted, so any suggestions?

Thank you in advance for your time and support.

Best wishes, Zhang