Tensorflow Check Failed: Status == Cudnn_status_success (7 Vs. 0)failed To Set Cudnn Stream

When I run my tensorflow keras model it will sometimes stop after an epoch and throw the following error: tensorflow/stream_executor/dnn.cc:613] CUDNN_STATUS_EXECUTION_FAILED in te

Solution 1:

So I found the cause to the error, you need to downgrade your Nvidia drivers to version 431.36. Everything above that makes tensorflow crash in above mentioned manner.

Solution 2:

I had similar problem and realised that it is due to my tensor flow version. Try this snippet.

import tensorflow.compat.v1 as tf

tf.disable_v2_behavior()  #disable for tensorFlow V2
physical_devices = tf.config.experimental.list_physical_devices('GPU')
tf.config.experimental.set_memory_growth(physical_devices[0], True)

Solution 3:

For anybody who's still getting this error: Downgrading is not needed. Only these lines are:

physical_devices = tf.config.experimental.list_physical_devices('GPU')
tf.config.experimental.set_memory_growth(physical_devices[0], True)