Clarify override of non-trainability of layers when model is created.

[microprediction]

trafficstars

URL(s) with the issue:.

https://keras.io/guides/transfer_learning/

Description of issue (what needs to be changed):.

Unless I am mistaken (and I may well be) there is no point in setting a layer to be non-trainable prior to construction of the model. This property will be ignored, as this gist demonstrates. Instead one must access the layer after the model is created.

[tilakrayal]

@microprediction, Could you please feel free to submit a PR for the requested change to be made. Thank you!

[microprediction]

Sure thanks

[tilakrayal]

@microprediction, Could you please feel free to submit a PR for the requested change to be made and provide the PR number for the tracking. Thank you!

[google-ml-butler[bot]]

This issue has been automatically marked as stale because it has no recent activity. It will be closed if no further activity occurs. Thank you.

[google-ml-butler[bot]]

Closing as stale. Please reopen if you'd like to work on this further.

[aliakdeniz38]

unsubscribe

On Tue, Sep 6, 2022 at 9:50 AM Peter Cotton @.***> wrote:

Sure thanks

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: @.***>