shayannikoohemat

If you have camera parameters( and rotation(YPR) and translation(XYZ) you can do the reconstruction directly from this information. For larger projects, you can use Pix4d.com.

@conby and @andimo11 Any update on this? The same problem here with `Cuda Version: 11.0` and `Torch Version: 1.8.2`. It works on CPU but not CPU. I used `requirements-torch-cuda.txt` to...

I think there is a typo in this line: `reaA = resA.replace_feature(self.bn1(resA.features))` should be: `resA = resA.replace_feature(self.bn1(resA.features))`

Did you solve this issue? I have the same problem on Mac.

It looks like Open3d-Ml `v0.15.1` needs `pytorch==1.12.0` but `pip install torch` on Mac M1 installs `pytorch 1.13`, this is why we get this error: `Exception: Open3D was not built with...

@kukuruza The GPU that I tested was: `NVIDIA GeForce GTX 1650`

I get the same error. I'm running on my data with 8 classes instead of 40. ` vec_conf = np.bincount(true * num_classes + pred) ValueError: operands could not be broadcast...

ok, found the issue, in the file `ModelNet40.py` the number of test and train samples are hard coded: ``` # Number of models and models used per epoch if self.train:...