Can't load davis best model

[eppoj]

When trying to load the Davis model I get the following errors.

https://pastebin.com/sx80tfTD

[kjaleph]

Please don't pass the full model file name. Example:
File name: model.best.data-00000-of-00001
You should pass: model.best

[eppoj]

Thank you that was the problem (learned something). However now I'm running into memory issues (OOM when allocating tensor with shape). I'm trying to run the software on an nvidia jetson nano, any suggestions to reduce the memory load?

[antonilo]

you could try to make the model smaller and train it again!

[karanjakhar]

Thank you that was the problem (learned something). However now I'm running into memory issues (OOM when allocating tensor with shape). I'm trying to run the software on an nvidia jetson nano, any suggestions to reduce the memory load?

import tensorflow as tf
physical_devices = tf.config.experimental.list_physical_devices('GPU')
assert len(physical_devices) > 0, "Not enough GPU hardware devices available"
config = tf.config.experimental.set_memory_growth(physical_devices[0], True)

Please execute the above code before loading any model.

[eppoj]

@karanjakhar where should I execute this code ?

[kjaleph]

Before loading anything. Below import libraries.

…

On Wed, Nov 18, 2020, 3:02 PM eppoj ***@***.***> wrote: @karanjakhar <https://github.com/karanjakhar> where should I execute this code ? — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#12 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ARRQJD6723RZW5KDKWL2EILSQOIDJANCNFSM4TXAOTKQ> .