Pedram Pejman
Pedram Pejman
I believe using protoc orthogonal to bazel is not the correct way of going about this - the correct way would be to add a `go_proto_library` for every `serving_proto_library`and let...
Sorry for the delay. Unfortunately adding logic to allow serving metadata other than signaturedefs is not on the roadmap right now and I'm not sure we have a good understanding...
@martinz is this a use case that ml metadata could be useful for?
@hmeine Thanks for the concrete use case - it makes sense and if you don't mind I'd like to understand the set up a little deeper to validate whether serving...
It's a reasonable request. For the short term, you can build ops into modelserver using this [guide](https://github.com/tensorflow/serving/blob/master/tensorflow_serving/g3doc/custom_op.md). However, as you noted, the dev experience would be much neater if you...
I see - so in order to have officially support tf.io ops we need to get a better understanding of their policies (I've asked a question in the issue you...
That works. Please ensure to include example requests as well. Thanks @Ouwen !
Hi all, just a note that I'm following up on this in the sister [issue](https://github.com/tensorflow/serving/issues/1411) - from tf serving perspective, we are extremely conscious about op robustness and supportability. What...