hugstar comments

Repositories
Issues
Comments

Results 4 comments of


                                            hugstar

Segmentation fault: 11 when running onnx_to_coreml.py

I've had the same issue. I was able to fix this by compiling ONNX from source.

Segmentation fault: 11 when running onnx_to_coreml.py

@Seanbakko Yes - what fixed it for me was compiling **both** Pytorch and ONNX from source and it solved the issue completely.

conv_faster in HW1

Great. Thanks! Will change.

dists = dists * tf.linalg.norm(rays_d[..., None, :], axis=-1)

`dists` are relative to the direction vector size. So for example, those 3 cases are exactly same for a given ray: - ray direction = (1, 2, 3), dist =...