Leonardo Apolonio

the development branch allowed for the js source code to be loaded and instrumented. i was wondering if you knew of any other issues with the google closure library? the...

Upon further investigation my tests are not using the in-memory instrumented files. How does mocha know which version of the source to use? Could it be an issue with my...

homonyms lookup - http://www.speech.cs.cmu.edu/cgi-bin/cmudict

@sminder thanks for the input. I think your feedback worked because the `saved_model_cli` is able to read the saved model. `saved_model_cli show --all --dir $PROJECT_HOME/export_t/1544203049` ``` MetaGraphDef with tag-set: 'serve'...

@neutronest @wazzy it looks like in https://github.com/bigboNed3/bert_serving run_classifier forgot to skip `init_from_checkpoint` when exporting the model. i'm working on an end to end example. my input_fn: ``` def serving_input_fn(): with...

@ahzz1207 I created an example of serving in google cloud platform using Kubernetes. https://github.com/lapolonio/bert/blob/classify_ag_news/make_containers.sh are the commands. I'm writing a post for medium. https://medium.com/@lapolonio/enterprise-solution-for-text-classification-using-bert-9fe2b7234c46 Feedback appreciated!

@Olivia-xu No. What is your error? I have a walkthrough here: https://medium.com/@lapolonio/enterprise-solution-for-text-classification-using-bert-9fe2b7234c46 Feedback appreciated!

@shawei3000 Thanks for the feedback! I just forced the version to be Tensorflow==1.12 and it's working again. P.S. if you could give feedback in the medium post that would help...

@Gpwner you didn't use tensorproto to make the message https://github.com/lapolonio/bert/blob/classify_ag_news/run_app.py#L48

@yajian how did you get that error? at the top of the script, I install tensorflow==1.12 https://colab.research.google.com/gist/lapolonio/5ac6552fa4d58ea1419cc444d42ff5ff/bert-finetuning-with-cloud-tpu-sentence-and-sentence-pair-classification-tasks.ipynb#scrollTo=Ns3IlhryMY-f