Why is there an error “invalid data input” when I try to test a successfully deployed ML model?
Alice
I followed a sample notebook to create a IBM cloud machine learning model using scikit-learn. The tutorial can be found here.
Every cell runs correctly and the model is deployed successfully, but when I click into the model and try to make a prediction, an error “Invalid input data” shows up. Why does this issue occur and how should I solve this?
wml_credentials = {
"username": "****",
"password": "****",
"instance_id": "****",
"url": "https://ibm-watson-ml.mybluemix.net”
}
When creating the API client, I tried changing the url from "https://ibm-watson-ml.mybluemix.net” to "https://us-south.ml.cloud.ibm.com”.
I also tried adding the access key like:
wml_credentials = {
"access_key”: "****",
"username": "****",
"password": "****",
"instance_id": "****",
"url": "https://ibm-watson-ml.mybluemix.net”
}
Nothing helped.
Vidyasagar Machupalli
Instead of passing individual values for f0,f1,f2..... You can pass the input as JSON shown below
{
"fields" : [ "f0", "f1", "f2", "f3", "f4", "f5", "f6", "f7", "f8", "f9", "f10", "f11", "f12", "f13", "f14", "f15", "f16", "f17", "f18", "f19", "f20", "f21", "f22", "f23", "f24", "f25", "f26", "f27", "f28", "f29", "f30", "f31", "f32", "f33", "f34", "f35", "f36", "f37", "f38", "f39", "f40", "f41", "f42", "f43", "f44", "f45", "f46", "f47", "f48", "f49", "f50", "f51", "f52", "f53", "f54", "f55", "f56", "f57", "f58", "f59", "f60", "f61", "f62", "f63" ],
"values" : [ [ 0.0, 5.0, 12.0, 13.0, 16.0, 16.0, 2.0, 0.0, 0.0, 11.0, 16.0, 15.0, 8.0, 4.0, 0.0, 0.0, 0.0, 8.0, 14.0, 11.0, 1.0, 0.0, 0.0, 0.0, 0.0, 8.0, 16.0, 16.0, 14.0, 0.0, 0.0, 0.0, 0.0, 1.0, 6.0, 6.0, 16.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 5.0, 16.0, 3.0, 0.0, 0.0, 0.0, 1.0, 5.0, 15.0, 13.0, 0.0, 0.0, 0.0, 0.0, 4.0, 15.0, 16.0, 2.0, 0.0, 0.0, 0.0 ] ]
}
Attaching is a screenshot on how to pass JSON input under deployment
I just verified the notebook and you don't have to change the ML URL.
Collected from the Internet
Please contact [email protected] to delete if infringement.
edited at
- Prev: Searching for a term as both a single string and multi worded string
- Next: How to extract strings before and after a delimiter and store in mysql?
Related
TOP Ranking
- 1
Failed to listen on localhost:8000 (reason: Cannot assign requested address)
- 2
Loopback Error: connect ECONNREFUSED 127.0.0.1:3306 (MAMP)
- 3
How to import an asset in swift using Bundle.main.path() in a react-native native module
- 4
pump.io port in URL
- 5
Compiler error CS0246 (type or namespace not found) on using Ninject in ASP.NET vNext
- 6
BigQuery - concatenate ignoring NULL
- 7
ngClass error (Can't bind ngClass since it isn't a known property of div) in Angular 11.0.3
- 8
ggplotly no applicable method for 'plotly_build' applied to an object of class "NULL" if statements
- 9
Spring Boot JPA PostgreSQL Web App - Internal Authentication Error
- 10
How to remove the extra space from right in a webview?
- 11
java.lang.NullPointerException: Cannot read the array length because "<local3>" is null
- 12
Jquery different data trapped from direct mousedown event and simulation via $(this).trigger('mousedown');
- 13
flutter: dropdown item programmatically unselect problem
- 14
How to use merge windows unallocated space into Ubuntu using GParted?
- 15
Change dd-mm-yyyy date format of dataframe date column to yyyy-mm-dd
- 16
Nuget add packages gives access denied errors
- 17
Svchost high CPU from Microsoft.BingWeather app errors
- 18
Can't pre-populate phone number and message body in SMS link on iPhones when SMS app is not running in the background
- 19
12.04.3--- Dconf Editor won't show com>canonical>unity option
- 20
Any way to remove trailing whitespace *FOR EDITED* lines in Eclipse [for Java]?
- 21
maven-jaxb2-plugin cannot generate classes due to two declarations cause a collision in ObjectFactory class
Comments