Can GGML apply in CNN or RCNN ?

[znsoftm]

This quantization scheme can speed up the inference of neural networks, but there still is less example in CNN or RCNN, even RNN. Is these ones not easy on ggml or other reasons?

[ggerganov]

It's a matter of implementing the necessary operators. Still, the code base can easily grow out of control, so I'm trying to take it slowly and keep it manageable. Thinking about adding support for implementing custom operators in the user-code.

Anyway, I hope we will eventually provide CNN examples with ggml

[znsoftm]

thanks:)