Parth Natekar

Hi, Where exactly is ```model.forward_dummy``` defined? Does it return the output of each module as an iterator? I can see that it returns a tuple of tensors, but I'm not...

Just to clarify, I'm using mmdet for bounding box prediction and then feeding that to a pose model. When I run ```forward_dummy``` on the mmdet model I get an output...

@Cong222 @ChristieLin Can you elaborate how you used this loss function with Keras with incompatible **y_true** and **y_pred** shapes?

@ludwigschubert Can you please elaborate exactly what I need to do to export my keras model? Do I need to follow the modelzoo tutorial and convert it to a graph...

Its Ubuntu 18.04

Hi, any updates on this, still getting the same error!

Hi, Thanks for your updates. I was able to install and import llspy using the above. I'm closing this for now but I'll let you know if I have any...

Hi, getting the following error now on running ```process``` or ```autoprocess```: ``` llspy.exceptions.CUDAbinException: cudadecon could not be located or is not executable: ```

Here is the output. I can see CudaDecon here. ``` # Name Version Build Channel _libgcc_mutex 0.1 conda_forge conda-forge _openmp_mutex 4.5 1_gnu conda-forge alabaster 0.7.12 pypi_0 pypi appdirs 1.4.4 pypi_0...

Hi, any updates on this? I believe it is just a question of pointing LLSPY to the cudaDecon installation.