python code for Auto Scaling Azur ML
Budget: $250 – $750 CAD
PROVE YOU CAN DO IT: show past azure ML projects WITH SCALING
0. I do not want to use your azure account at all for my testing, use your Azure by yourself only for development. But I test on my account
1. ML project end to end development on Azur
2. Any python package installed by pip can be used for this ML project
3. Build with Automatic scaling a customized model training for python code ML model provided by me or you can use your code if I like it
4. Build with Automatic scaling a customized inference
5. Automatic scaling, load balancing to handle 1234 requests/sec, requests done by python from any local computer on web
6. many VMs Distributed training with Hyperparameters search
7. possibly many VMs Distributed Preprocessing
8. many VMs Distributed Inference
9. requests implemented by python for predictions may be done from any computer on web no credentials needed (not ssh or any remote connection to azure)
10. no GUI design, but all done by python SDK
11. basic idea ML starter code and data will be provided
12. YOU PROVIDE PYTHON CODE AND VIDEO WITH EXPLANATIONS STEP BY STEP HOW TO DO and how to use
---------------------------------------------------------------
PROJECT ACCEPTANCE : I CAN DO BY MYSELF on my azure account
----------------------------------------------------------------
TIME MAX 1 WEEK
Testing :
1 for predictions I use your python code which hosted on my Azure cloud project created by me using your instructions.
2 Make sure there are no dropped requests ( requests without response )
3 Many requests are sent in parallel by python (as much as 1234 per second ) runs on local computer and makes automatic request , for requests use data from test data set
4 send request with text for prediction and request id (generate random id in request to confirm it is the same request text what was sent for prediction)
5 send back Response from inference prediction ( 0 or 1) and same request id
6 When predictions are received: unique ID is used to match prediction and request text
7 Calculate performance : statistics for valid responses and correct predictions : confusion matrix , etc
for ML details see files uploaded
https://www.freelancer.com/projects/python/python-code-for-Auto-Scaling/files
0. I do not want to use your azure account at all for my testing, use your Azure by yourself only for development. But I test on my account
1. ML project end to end development on Azur
2. Any python package installed by pip can be used for this ML project
3. Build with Automatic scaling a customized model training for python code ML model provided by me or you can use your code if I like it
4. Build with Automatic scaling a customized inference
5. Automatic scaling, load balancing to handle 1234 requests/sec, requests done by python from any local computer on web
6. many VMs Distributed training with Hyperparameters search
7. possibly many VMs Distributed Preprocessing
8. many VMs Distributed Inference
9. requests implemented by python for predictions may be done from any computer on web no credentials needed (not ssh or any remote connection to azure)
10. no GUI design, but all done by python SDK
11. basic idea ML starter code and data will be provided
12. YOU PROVIDE PYTHON CODE AND VIDEO WITH EXPLANATIONS STEP BY STEP HOW TO DO and how to use
---------------------------------------------------------------
PROJECT ACCEPTANCE : I CAN DO BY MYSELF on my azure account
----------------------------------------------------------------
TIME MAX 1 WEEK
Testing :
1 for predictions I use your python code which hosted on my Azure cloud project created by me using your instructions.
2 Make sure there are no dropped requests ( requests without response )
3 Many requests are sent in parallel by python (as much as 1234 per second ) runs on local computer and makes automatic request , for requests use data from test data set
4 send request with text for prediction and request id (generate random id in request to confirm it is the same request text what was sent for prediction)
5 send back Response from inference prediction ( 0 or 1) and same request id
6 When predictions are received: unique ID is used to match prediction and request text
7 Calculate performance : statistics for valid responses and correct predictions : confusion matrix , etc
for ML details see files uploaded
https://www.freelancer.com/projects/python/python-code-for-Auto-Scaling/files