Python -c "import cntk print(cntk.version)" Your Keras code does not need to be modified (I checked it with 2 examples of Keras using TensorFlow and succesfully replaced TensorFlow with CNTK, without changing anything the Keras code. According to Jeong-Yoon Lee CNTK is a lot (about 2 to 4 times) faster than TensorFlow for LSTM (Bidirectional LSTM on IMDb Data and Text Generation via LSTM), while speeds for other type of neural networks are close to each other. If you only need TensorFlow because of Keras and your are on Python 2.7.x, you can avoid installing Tensorflow(Google) and replace it by CNTK(Microsoft). Looking around, I saw this on Stack Overflow:
It's an older Keras which was not as tightly bound to Tensorflow, in fact would support a couple of other back end engines.
0 kommentar(er)
