Antonin Sumner

Missing ReLU in notebook 06 part 2

1

Fast.ai Deep Learning Course Part 2, notebook 06_cuda_cnn_hooks_init: When we refactor the CNN model builder I think the ReLUs after the Conv2D are missing: 

Onnx export from mmdet retinanet ?

2

Is there a convenient way to export models to ONNX? I have a pretty satisfying mmdet.retinanet model with backbone resnet50_fpn_1x but I have a hard time exporting it to ONNX...

pip error 400 for torch cuda wheel files

1

### Checklist - [X] I have searched for [similar issues](https://github.com/isl-org/Open3D-ML/issues). - [X] I have tested with the [latest development wheel](http://www.open3d.org/docs/latest/getting_started.html#development-version-pip). - [X] I have checked the [release documentation](http://www.open3d.org/docs/release/) and the...

Question about Semantic3d data preparation. Why are we converting point clouds to .npy instead of .ply format? Is this more convenient when using PyTorch? faster to read? I have seen...

Invalid MEX file: correspondPixels.mexmaci64

2

Hello, I'm trying to use your evaluation code on MATLAB (r2019b) on mac os x but I get this error: `Error using edgesEvalImg (line 70) Invalid MEX-file '/Users/antoninsumner/Documents/GitHub/EdgeDetection_ModelsComparison/eval/edges/private2/correspondPixels.mexmaci64': dlopen(/Users/antoninsumner/Documents/GitHub/EdgeDetection_ModelsComparison/eval/edges/private2/correspondPixels.mexmaci64, 6):...

[orx-kdtree] Allow the KDTree to return the KNN points indices instead of coordinates.

3

### Motivation The KDtree queries should allow to return the indices of the points instead of the coords. Do you think this implementation could be easily updated for this feature...

I 'm trying to combine crowd-semantic-segmentation and crowd-polyline and it seems that aws GT will take only one of these. Is it possible to actually combine those crowd elements? and...