Open martyLY opened 1 year ago
Thanks for using our code!
You can git checkout 851af85349
to the initial release.
Many thanks for sharing your DVGO code.
I have switched to 851af85349
. But I ran into another issue when "python run.py --config configs/nerf/lego.py --render_test" as below. Could you shed some light on this?
File "run.py", line 425, in train scene_rep_reconstruction( File "run.py", line 254, in scene_rep_reconstruction model, optimizer, start = utils.load_checkpoint( File "/home/jerry/nf_v2/DirectVoxGO/lib/utils.py", line 203, in load_checkpoint model.load_state_dict(ckpt['model_state_dict']) File "/home/jerry/anaconda3/envs/nf_v2/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1497, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for DirectVoxGO: Missing key(s) in state_dict: "density", "k0". Unexpected key(s) in state_dict: "act_shift", "mask_cache.mask", "mask_cache.xyz2ijk_scale", "mask_cache.xyz2ijk_shift".
Please forget about my previous question. After deleting logs/ folder when switching to the older version, the "Unexpected key" issue was fixed.
Thanks for sharing this amazing work !👍👍
My team is following your work and I need to do a comparative experiment between DVGOv1 and DVGOv2, so can you release or share DVGOv1 source code (w/o cuda and distortion loss)?
Thank for your time and looking forward to your future work!