21 lines
332 B
Markdown
21 lines
332 B
Markdown
Troubleshooting TensorFlow / KERAS GPU Process
|
|
==============================================
|
|
|
|
|
|
Common issues:
|
|
|
|
* Model too big
|
|
(print the KERAS model---is the number of parameters doable with the GPU?)
|
|
|
|
* Batch size too large
|
|
|
|
* Memory not released from previous processing
|
|
|
|
(use `with tf.Session() as sess:` code block)
|
|
|
|
|
|
|
|
|
|
|
|
|