You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@beam.apache.org by Jack McCluskey via dev <de...@beam.apache.org> on 2023/01/03 15:27:26 UTC

TensorFlow Hub Integration in RunInference

Hey everyone,

I've put together some thoughts on how we would allow users to load
pre-trained models from TensorFlow Hub into RunInference pipelines in a
small doc:
 https://docs.google.com/document/d/11WpWQ_x3dpgRTvkzKS47lCXA_-PGzUBAIKNJQfLpJTg/edit?usp=sharing
<https://docs.google.com/document/d/11WpWQ_x3dpgRTvkzKS47lCXA_-PGzUBAIKNJQfLpJTg/edit?usp=sharing>

PTAL if you're interested.

Thanks,

Jack McCluskey

-- 


Jack McCluskey
SWE - DataPLS PLAT/ Dataflow ML
RDU
jrmccluskey@google.com

Re: TensorFlow Hub Integration in RunInference

Posted by Danny McCormick via dev <de...@beam.apache.org>.

Thanks Jack - I had a single question about the tfx-bsl limitations, but
otherwise this looks great to me!

On Tue, Jan 3, 2023 at 10:27 AM Jack McCluskey via dev <de...@beam.apache.org>
wrote:

> Hey everyone,
>
> I've put together some thoughts on how we would allow users to load
> pre-trained models from TensorFlow Hub into RunInference pipelines in a
> small doc:
>  https://docs.google.com/document/d/11WpWQ_x3dpgRTvkzKS47lCXA_-PGzUBAIKNJQfLpJTg/edit?usp=sharing
> <https://docs.google.com/document/d/11WpWQ_x3dpgRTvkzKS47lCXA_-PGzUBAIKNJQfLpJTg/edit?usp=sharing>
>
> PTAL if you're interested.
>
> Thanks,
>
> Jack McCluskey
>
> --
>
>
> Jack McCluskey
> SWE - DataPLS PLAT/ Dataflow ML
> RDU
> jrmccluskey@google.com
>
>
>