After designing and training, the model file needs to be converted into a ".dlc" (Deep Learning Container) file to be used by the Snapdragon NPE runtime.
I have a project on behavior recognition based on 3D convolution, and I would like to ask whether SNPE also supports 3D convolution, that is, whether models based on 3D convolution can also be converted into ".dlc " files to be used by the Snapdragon NPE runtime.
Hi,
Snapdragon NPE doesn't support 3D convolutions.
It is known that 3D convolution requires 4D input which is not supported by in NPE.