Prerequisites

Please answer the following question for yourself before submitting an issue.

• [X] I checked to make sure that this feature has not been requested already.

1. The entire URL of the file you are using

https://github.com/tensorflow/models/blob/master/official/projects/vit/modeling/vit.py

2. Describe the feature you request

For some feature types, especially of low dimension, projection doesn't suit. I wish that there were somehow to turn off the projection, so one can use directly the encoder. I tried to use the Encoder class directly, but it seems like an internal component and I get a funny error when I try to use it.

3. Additional context

Add any other context about the feature request here.

4. Are you willing to contribute it? (Yes or No)

Yes

Hi @exx8,

Would you like to submit the PR or if you already have one, can you please attach here ?

Thanks.

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you.

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you.

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