Huang Zhuangze

> Thanks for replying. I recently tried to train an ancient Chinese language Albert with my own corpus using google-research Albert, the error occurred when I used it into downstream...

> @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:...

> @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! Hi, i corrected...

> @lapolonio many thanks for the reply. > I have created a pull request and uploaded run_classifier.py. > I am new to the github pull requests also, so hope I've...

> > > @lapolonio many thanks for the reply. > > > I have created a pull request and uploaded run_classifier.py. > > > I am new to the github...

> @ahzz1207 I got it here thank you https://github.com/ahzz1207/Bert-with-text-classification-and-service. > So I see you have test_serving_model.py as a version of run_classify.py . > First thing I notice is that you...

Hello , I used the original data set on your cloud disk, ran 1000 epoch with the original parameter keras model, and the chunksize was 200,000.However, the best val_loss of...