Adrián Rodríguez Grillo

> In the orientation decode process, what we regress is the angle between the camera ray and the heading orientation (as can be seen in Fig. 4 of our paper)....

I understand and, therefore, all this transformations are done in https://github.com/lzccccc/SMOKE/blob/master/smoke/modeling/smoke_coder.py#L212-L234. Is that correct? However, my question in this regards goes into the lines https://github.com/lzccccc/SMOKE/blob/master/smoke/modeling/smoke_coder.py#L236-L245. This block is only executed...

For my use case, I removed that flipping part in the training code and worked perfectly. If you need to explain the code lately, I recommend doing the same.

Yes, that could happen or even started to increase. I have tried stopping the training and starting the process again with the last weights saved, restarting the optimizer. However, you...

This should be fixed now with the change from `np.int` to `np.int32` here: ```python height_split = np.linspace(0, height, n + 1, dtype=np.int32) width_split = np.linspace(0, width, m + 1, dtype=np.int32)...

Hello, Try to set `ONNXRUNTIME_DIR` with the location where you have installed the onnx-runtime changing the following lines. ```bash export ONNXRUNTIME_DIR="path to onnx-runtime" export LD_LIBRARY_PATH=$ONNXRUNTIME_DIR/lib:$LD_LIBRARY_PATH ``` That solved the problem...