tfdeploy

tfdeploy copied to clipboard

TensorFlow Model Serving in Connect is deprecated

1

TensorFlow Model serving in Connect is deprecated as of the September 2022 edition release. Support will be removed in a future release. We're recommending folks use an API framework like...

kellobri

Error while trying to reproduce "Getting Started" example.

2

I am not being able to reproduce the example given in [TensorFlow Model Deployment from R End-to-End section](https://rstudio.github.io/tfdeploy/#end-to-end-example). I am willing to export and then serve a keras model, however,...

jcrodriguez1989

mxnet backend keras is faster than tensorflow in below benchmark comparison, in that, wish to implement tfdepoly for mxnet. ## reference: https://github.com/awslabs/keras-apache-mxnet/blob/master/benchmark/README.md

harryprince

tfdeploy::serve_savedmodel predictions work locally, on RSC server they return {"error":"Error while attempting to parse predict request: json: cannot unmarshal number into Go value of type []float32"}

3

Hello, not sure how relevant to tfdeploy this is but just wanted to point it out. I've trained my own NN and successfully tested local deployment with the following json:...

spotcapkonradsemsch

export_savedmodel for tfestimators gives warning

8

If I add an `export_savedmodel()` call to this script: https://github.com/rstudio/tfestimators/blob/master/vignettes/examples/mnist.R The I get the following warning after calling export_savedmodel: WARNING:tensorflow:Export includes no default signature!

jjallaire

Predicting a tfestimators model after exporting without session restart fails

2

Run the following, notice that this is fixed if the r session is restarted after running `export_savedmodel()`. ```r library(tfestimators) mtcars_input_fn

javierluraschi