search

princeton-vl / DROID-SLAM

BSD 3-Clause "New" or "Revised" License
1.66k stars 273 forks source link

After training, the ckpt flie can not use? #43

Open xhangHU opened 2 years ago

xhangHU commented 2 years ago

0it [00:00, ?it/s]./checkpoints/bla_250000.pth /root/anaconda3/envs/droidenv5/lib/python3.9/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1639180487213/work/aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, *kwargs) # type: ignore[attr-defined] 51it [00:06, 7.47it/s] ################################ Traceback (most recent call last): File "/root/docker2/droid/2new/DROID-SLAM/demo.py", line 117, in traj_est = droid.terminate(image_stream(args.imagedir, args.calib, args.stride)) File "/root/docker2/droid/2new/DROID-SLAM/droid_slam/droid.py", line 81, in terminate self.backend(7) File "/root/anaconda3/envs/droidenv5/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 28, in decorate_context return func(args, *kwargs) File "/root/docker2/droid/2new/DROID-SLAM/droid_slam/droid_backend.py", line 33, in call graph.add_proximity_factors(rad=self.backend_radius, File "/root/docker2/droid/2new/DROID-SLAM/droid_slam/factor_graph.py", line 368, in add_proximity_factors ii, jj = torch.as_tensor(es, device=self.device).unbind(dim=-1) ValueError: not enough values to unpack (expected 2, got 0) Traceback (most recent call last): File "", line 1, in File "/root/anaconda3/envs/droidenv5/lib/python3.9/multiprocessing/spawn.py", line 116, in spawn_main exitcode = _main(fd, parent_sentinel) File "/root/anaconda3/envs/droidenv5/lib/python3.9/multiprocessing/spawn.py", line 126, in _main self = reduction.pickle.load(from_parent) File "/root/anaconda3/envs/droidenv5/lib/python3.9/multiprocessing/synchronize.py", line 110, in setstate self._semlock = _multiprocessing.SemLock._rebuild(state) FileNotFoundError: [Errno 2] No such file or directory [W CudaIPCTypes.cpp:15] Producer process has been terminated before all shared CUDA tensors released. See Note [Sharing CUDA tensors]

YznMur commented 2 years ago

Hi @xhangHU Have you managed to solve this problem?

519174419 commented 2 years ago

It maybe cause by, the distance of graph is loss than the thresh. Try to give a smaller thresh, the demo will run successfully. But I still meet some problem with the disps result

YznMur commented 2 years ago

Hi @519174419 you mean keyframe_thresh? can you please share your demo (inference) parameters?

xhangHU commented 2 years ago

It maybe cause by, the distance of graph is loss than the thresh. Try to give a smaller thresh, the demo will run successfully. But I still meet some problem with the disps result

do you mean n_frames in the parameter, i tried 3 and 4 and it doesn't work

xhangHU commented 2 years ago

Hi @519174419 you mean keyframe_thresh? can you please share your demo (inference) parameters?

Due to device limitations I can only use n_frames = 3 or 4 for training, other parameters are default values

YznMur commented 2 years ago

Hi @519174419 would you please share your demo (inference) parameters or training parameters so the ckpt file could work ?

519174419 commented 2 years ago

Hi @519174419 would you please share your demo (inference) parameters or training parameters so the ckpt file could work ? It's still some problem with my result, I am trying to solve it.

Aurora-chevalier commented 1 year ago

Hello, I can't read the image when training the tartan dataset, can you show the instructions you used to train the tartan dataset？ 1