Run NLP (tensorflow/pytorch) model - tensorflow

i'm newbie in datascience and i want to test this model with real data in RESTfull application
https://github.com/instadeepai/tunbert
anyone can help ? please

Related

Spacy train dev and test data

Does spaCy use dev-data to tune hyper-parameters? Or dev-data is totally out of the training process, and so equivalent to test data?
Following the standard greatly explained here, validation data and test data are different. Please is someone can clarify which is the case for spaCy under the referred standard. Thanks a lot.
The spacy core library does not do any hyperparameter tuning. For spacy train, the dev data is used for the evaluation displayed during training, to select the best model, and for early stopping (the early stopping setting is called patience).

How to deploy TensorFlow model to cloud?

I want to deploy my deep learning model to the cloud so that I can upload photos on an iPhone App and the model handles the detection and returns the output.
What would be the best way to do this?
Thank you!
There are multiple ways you can deploy a tensorflow model. Read through the following official documentation.
TensorFlow - Serving Models

How to tune learning rate with HParams Dashboard

In Tensorflow documentation, it is shown how to tune several hyperparameters but not the learning rate.I have searched how to tune learning rate using HParams dashboard but could not find much. The only example is another question on github but it does not work.Can you please give me some suggestions on this?Should I use a callback function?Or provide different learning rates in hp_optimizer as in the question in github? Or something else?
Thank you,

How to dynamically modify neural network with tensorflow during thetraining

I am trying to dynamically modify the neural network architecture(e.g, add/delete layer...) and hyperparameter during the training period on Tensorflow.(e.g.,control_func(#layer,#neuron,learning_rate...)) However, I have no idea how to implement it in the code. Could anyone can provide some reference, insight, or tutorial? Thanks a lot!

Chatbot: generative model using Python framework deployed in Slack

Could somebody tell me whether it is possible to develop a chatbot using python ML frameworks such as tensorflow and deploy in Slack using Slack's apps?
As far as I have read we could develop some retrieval based model using node.js. But I'm looking for a generative model.
Anything to help me get started is much appreciated.
Thanks!
In order to use a generative model you have to use tensorflow sequence to sequence architecture . Here's the official TF tutorial from TF on sequence-to-sequence architecture .
So after training the model you can set this as an API which is easy. Then may be you can set it with the slack API for sure.