Open johannesgensheimer opened 4 years ago
Hello, it is possible to change the backend of keras from tensorflow to theano. Explained here: https://stackoverflow.com/questions/42177658/how-to-switch-backend-with-keras-from-tensorflow-to-theano
But is it also possible to switch the backend of keras2onnx?
I'm working on a Jetson TX2 with Linux Ubuntu 16.04 and CUDA 9.0. Thanks for your help and please let me know if you need further information!
It's possible since all layer converter are independent from tf and only some changes needs for the parser.py. But I am not sure if there is anyone who will be willing to maintenance it.
Hello, it is possible to change the backend of keras from tensorflow to theano. Explained here: https://stackoverflow.com/questions/42177658/how-to-switch-backend-with-keras-from-tensorflow-to-theano
But is it also possible to switch the backend of keras2onnx?
I'm working on a Jetson TX2 with Linux Ubuntu 16.04 and CUDA 9.0. Thanks for your help and please let me know if you need further information!