Anass Yarroudh

Hello @WanpengShao, You can try to rename `radius_neighbors.cp39-win_amd64.pyd` to `radius_neighbors.pyd` and `grid_subsampling.cp39-win_amd64.pyd` to `grid_subsampling.pyd`. This solved the problem for me. @HuguesTHOMAS

Hello, If you want to compile under windows you should run the `build.bat` files under `cpp_neighbors` and `cpp_subsampling`. You need to change `py setup.py build_ext --inplace` to `python setup.py build_ext...

You can solve this by simply modifying your `utils/trainer.py`: [utils/trainer.py](https://github.com/HuguesTHOMAS/KPConv-PyTorch/blob/master/utils/trainer.py#L187-L190) ```python labels = torch.tensor(batch.labels, dtype=torch.long) loss = net.loss(outputs, labels) acc = net.accuracy(outputs, labels) ``` This solved the same problem for...

Hello @longmalongma, I think you can install `tensorflow

I could resolve this error by downsamling my images. The optimization command looks like this: `python localTensoRF\train.py --datadir ../scene --logdir ../scene/log --downsampling 2`

@ameuleman Thanks for your fast reply. I'm wondering if there is any way to reduce the optimization time.

Thanks for your reply. One last question, after optimization, the output includes the camera poses? If yes, which format? Thanks for your help and the amazing work.

So, if I understand, training takes so long, but how about predictions? I'm actually interested in these architectures because I wanted to reduce the processing time for scene reconstruction. Using...

> Can you please tell me whats the unit of RMSE. I used this method and got the final RMSE as 0.86 something. I gave the GCPs in the UTM...

Under the file `geometry.py` I found two functions `get_intrinsics` and `depth_to_points`. I think if we change `depth_to_points` to this, we can actually define the camera intrinsics and extrinsics as we...