Convolutional layer error using tf.agents with GPU activated

Asked Jun 17 '22 at 11:20

Active Jun 17 '22 at 11:20

Viewed 56 times

I running DQN training tutorial with tf.agents(https://www.tensorflow.org/agents/tutorials/1_dqn_tutorial), and I am trying to change the model they use with just dense layers to have some convolutional ones on top

When I run this on colab without GPU its all fine, but when I connect to GPU I get this error.

Is it because conv layers are not available yet with GPU with tf.agents or are there some dependencies extra that I have to install to be able to do this?

asked Jun 17 '22 at 11:20

José Luis Neves

This means it cannot find cuDNN, it should be in your library path. – Dr. Snoopy Jun 17 '22 at 12:14
But doesn't colab have cuDNN instaled by default? – José Luis Neves Jun 17 '22 at 16:10
"Cannot find" is not the same as "not installed", maybe it expects different versions, etc. – Dr. Snoopy Jun 17 '22 at 16:19

Convolutional layer error using tf.agents with GPU activated

0 Answers0