Keras with Tensorflow backend - Run predict on CPU but fit on GPU

python tensorflow keras keras-rl
Raphael Royer-Rivard picture Raphael Royer-Rivard · Jul 24, 2018 · Viewed 8.2k times · Source

I am using keras-rl to train my network with the D-DQN algorithm. I am running my training on the GPU with the model.fit_generator() function to allow data to be sent to the GPU while it is doing backprops. I suspect the generation of data to be too slow compared to the speed of processing data by the GPU.

In the generation of data, as instructed in the D-DQN algorithm, I must first predict Q-values with my models and then use these values for the backpropagation. And if the GPU is used to run these predictions, it means that they are breaking the flow of my data (I want backprops to run as often as possible).

Is there a way I can specify on which device to run specific operations? In a way that I could run the predictions on the CPU and the backprops on the GPU.

Answer

mss picture mss · Jul 28, 2018

Maybe you can save the model at the end of the training. Then start another python file and write os.environ["CUDA_VISIBLE_DEVICES"]="-1"before you import any keras or tensorflow stuff. Now you should be able to load the model and make predictions with your CPU.

Related questions

Can I run Keras model on gpu?

I'm running a Keras model, with a submission deadline of 36 hours, if I train my model on the cpu it will take approx 50 hours, is there a way to run Keras on gpu? I'm using Tensorflow backend and running it …

Read More
Keras, How to get the output of each layer?

I have trained a binary classification model with CNN, and here is my code model = Sequential() model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1], border_mode='valid', input_shape=input_shape)) model.add(Activation('relu')) model.add(Convolution2…

Read More
Tensorflow 2.0 - AttributeError: module 'tensorflow' has no attribute 'Session'

When I am executing the command sess = tf.Session() in Tensorflow 2.0 environment, I am getting an error message as below: Traceback (most recent call last): File "<stdin>", line 1, in <module> AttributeError: module 'tensorflow' has no attribute …

Read More