search

xingyizhou / pytorch-pose-hg-3d

PyTorch implementation for 3D human pose estimation
GNU General Public License v3.0
614 stars 143 forks source link

Question about dataset MPII #50

Open Ssrzbao opened 5 years ago

Ssrzbao commented 5 years ago

I have downloaded the MPII dataset, but what should I do to generate the .H5 file? Here are the problems I encountered during training. f = File('{}/mpii/annot/{}.h5'.format(ref.dataDir, split), 'r') File "D:\anaconda\envs\Pytorch3\lib\site-packages\h5py_hl\files.py", line 312, in init fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr) File "D:\anaconda\envs\Pytorch3\lib\site-packages\h5py_hl\files.py", line 142, in make_fid fid = h5f.open(name, flags, fapl=fapl) File "h5py_objects.pyx", line 54, in h5py._objects.with_phil.wrapper File "h5py_objects.pyx", line 55, in h5py._objects.with_phil.wrapper File "h5py\h5f.pyx", line 78, in h5py.h5f.open

xingyizhou commented 5 years ago

Hi, The h5 data is from the original torch Hourglass implementation from Newell et al., which looks like to be generated by this code.