Questions tagged [deployment]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
4 votes
2 answers
816 views

Do model training pipeline should run on dev, staging and production environment?

I know it's a best practice to ship our code from dev to staging to production by including different level tests and validations that will help to confidently deploy on the production environment. ...
1 vote
1 answer
26 views

Ways to share Pytorch model without revealing architecture?

We are trying to give a model to collaborators but would like to protect the IP. What are some ways to encrypt/hide/compile the definition when sharing a trained model?
  • 11
1 vote
1 answer
23 views

What is the best approach to deploy N number of ML models as a scalable service in the Cloud?

I've N (~50) number of sentiment models of different languages, which were fine tuned on HggingFace's transformer models. Each of the models as 2-3 GB in size approx. Now, how can I deploy all these ...
0 votes
0 answers
8 views

Can accuracy improve when there is evidence of domain-shift between training and deployment?

A model for image analysis was trained using data captured with imaging system A. I then deployed the model on imaging system B. System B has better image contrast than system A. Features in the last ...
  • 1
0 votes
0 answers
88 views

How to use early_stopping_rounds in the Final Model? (CatBoost example with Optuna)

Imagine we have a model in the sklearn pipeline: ...
0 votes
2 answers
44 views

Which random_state to use in test_train_split when deploying final model?

I have developed a Random Forest that gives varying results depending on the random state of the test train split. This is normal, because a lot of the values in the data are extreme, without being ...
0 votes
1 answer
21 views

After experimentation, how do we learn a final model for deployment?

I have a question regarding learning a "final" model for deployment. Assuming my task is a classification one, my workflow during experimentation is as follows. Get the data: ...
0 votes
0 answers
2k views

ValueError: dtype='numeric' is not compatible with arrays of bytes/strings.Convert your data to numeric values explicitly instead

I am new to machine learning model deployment. In a sequence, local system rises an error while running "app.py" file, that is: ...
0 votes
0 answers
29 views

Can I use Population Stability Index (PSI) when observations have multiple variables?

I understand from resources like this one that the Population Stability Index (PSI) can be used to test for data drift when a machine learning model is in production. However, the resources I have ...
0 votes
0 answers
9 views

Shadow deployment vs batch prediction on log?

In shadow deployment we 1) deploy a new model in parallel with the existing one; 2) route every incoming request to both the existing and candidate model; 3) serve the existing model's predictions for ...
1 vote
0 answers
5 views

How is model scheduling set up in practice?

I have been working on various machine learning models so far, but never yet on the deployment phase of an ML project. I have vaguely used Apache Airflow and I'm aware that it is a tool for scheduling ...
  • 289
0 votes
0 answers
401 views

How To Scale a multiple columns using a MinMaxScaler() using the pickled file during deployment of the model?

I am trying to deploy an ml model. As a part of processing the data, I am scaling my data. I pickled the scaler and need to do the same in my deployment code. But I am not able to do it correctly. ...
1 vote
0 answers
1k views

FileNotFoundError: Unsuccessful TensorSliceReader constructor

I am trying to deploy my model. I am encountering the following problem: FileNotFoundError: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for ram://a603e930-4fda-4105-...
0 votes
0 answers
6 views

Deploying Azure ML Web Service in Flask

I have trained a predictive model on Azure ML Studio, and deployed it as a web service. I have the API key Azure ML gave me. I want to take user input on my own Flask app and get the prediction from ...
  • 1
0 votes
0 answers
39 views

Deploy ML model on java web server or on python web application

Newbie here and I only have experience in training machine learning models on Jupyter notebook along with test/validate the model accuracy. I would like to move on and learn how I can deploy machine ...
0 votes
0 answers
35 views

How to create recommendation systems that are suitable for deployment in production environment for an ecommerce giant?

I am making a recommendation model for an ecommerce client that has huge number of products of various categories. Product data set can be considered similar to that of Amazon. For now, I am starting ...
  • 1
1 vote
1 answer
144 views

How to handle categorical feature engineering in ML production?

I have a classification dataset ,where I have a lot of categorical columns . I have one hot encoded ie. dummy variables in my training . How to handle this in production side of ML. There are cases ...
  • 198