IBM Data and AI Ideas Portal for Customers


Shape the future of IBM!

We invite you to shape the future of IBM, including product roadmaps, by submitting ideas that matter to you the most. Here's how it works:

Post your ideas

Post ideas and requests to enhance a product or service. Take a look at ideas others have posted and upvote them if they matter to you,

  1. Post an idea

  2. Upvote ideas that matter most to you

  3. Get feedback from the IBM team to refine your idea

Help IBM prioritize your ideas and requests

The IBM team may need your help to refine the ideas so they may ask for more information or feedback. The product management team will then decide if they can begin working on your idea. If they can start during the next development cycle, they will put the idea on the priority list. Each team at IBM works on a different schedule, where some ideas can be implemented right away, others may be placed on a different schedule.

Receive notification on the decision

Some ideas can be implemented at IBM, while others may not fit within the development plans for the product. In either case, the team will let you know as soon as possible. In some cases, we may be able to find alternatives for ideas which cannot be implemented in a reasonable time.

Additional Information

To view our roadmaps: http://ibm.biz/Data-and-AI-Roadmaps

Reminder: This is not the place to submit defects or support needs, please use normal support channel for these cases

IBM Employees:

The correct URL for entering your ideas is: https://hybridcloudunit-internal.ideas.aha.io


Status Not under consideration
Workspace Visual Recognition
Created by Guest
Created on Aug 4, 2020

The Lite Plan is Very Restricted

I started using the Lite plan to learn a few things about IBM's APIs, due to the Behid the Code Marathon which will start soon.

I started using Visual Reconition, training to do river and sea photo recognition.

I hardly used it and it reached its limit.

I think that maybe it could have to do with me sending a lot of images to train him (around 1600 images, 800 from the river, and 800 from the sea)

I realized this need, because using only 10 images he was not very good at differentiating between river and sea, I got to test it and it was much better after I trained him with many images.

Then I decided to create a NodeJS code based on an example from the IBM documentation and started testing, I really shouldn't have tested even 50 images and it has reached its limit.

I would like to know if sending too many images to train makes Plano Lite reach its limit and how can I recover the Lite plan to participate in the Marathon?

I would like to take advantage and report that the "implementation" tab where it shows the code to be implemented in languages ​​like Python and Node are giving a "depracation" error. That says DeprecationWarning: VisualRecognitionV3 is a deprecated function. watson-developer-cloud moved to ibm-watson, luckily i saw another documentation where it shows the code, but i think this makes it difficult for beginners like me, i had to search until i found the solution, which is in IBM's own documentation.

---------------

The depreciated code displayed is:

import json

from watson_developer_cloud import VisualRecognitionV3

visual_recognition = VisualRecognitionV3 (

'2018-03-19',

iam_apikey = '{iam_api_key}')

with open ('./ fruitbowl.jpg', 'rb') as images_file:

classes = visual_recognition.classify (

images_file,

threshold = '0.6',

classifier_ids = 'MarouRio_1704349307'). get_result ()

print (json.dumps (classes, indent = 2))

-----

I hope this helps them to get better, this is my feedback, with love.

  • Admin
    SABTAIN KHAN
    Sep 9, 2020

    The service is priced in a way where you can get a whole month of usage for free at your level after upgrading if you're a first time Cloud user. I would also point out that Lite is really meant for minimal testing, not to build a solution with hundreds of images used to train a model.