search

karfly / learnable-triangulation-pytorch

This repository is an official PyTorch implementation of the paper "Learnable Triangulation of Human Pose" (ICCV 2019, oral). Proposed method archives state-of-the-art results in multi-view 3D human pose estimation!
MIT License
1.09k stars 181 forks source link

Error wrapping 3D keypoints, bounding boxes and camera intrinsics together #87

Closed jamalknight closed 4 years ago

jamalknight commented 4 years ago

I get an error in step 6 in the pre processing scripts section - Wrapping 3D keypoints, bounding boxes and camera intrinsics together: (other than the warning of 'camera 54138969 isn't present in S11/Directions-2)

Command: python3 generate-labels-npy-multiview.py ../../../data/human36m/ ../../../data/human36m/extra/una-dinosauria-data/ ../../../data/human36m/extra/bboxes-Human36M-GT.npy

Error: Traceback (most recent call last): File "generate-labels-npy-multiview.py", line 58, in cameras_params = h5py.File(os.path.join(una_dinosauria_root, 'cameras.h5'), 'r') File "/home/jamal/.local/lib/python3.6/site-packages/h5py/_hl/files.py", line 408, in init swmr=swmr) File "/home/jamal/.local/lib/python3.6/site-packages/h5py/_hl/files.py", line 173, 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 88, in h5py.h5f.open OSError: Unable to open file (unable to open file: name = '../../../data/human36m/extra/una-dinosauria-data/cameras.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)

shrubb commented 4 years ago

Make sure you've extracted 'h36m.zip' at a previous step correctly so that ../../../data/human36m/extra/una-dinosauria-data/cameras.h5 exists.

jamalknight commented 4 years ago

Thats right. It was in a subfolder 'H36M' that was created when extracted. Thanks