How to Create an AI Service for Image Recognition
How to Create an AI Service for Image Recognition:
Make sure to visit: app.cogniflow.ai
Then log in to the platform with user and password
If you don’t have a user account please create one for free here: Sign Up
Home page shows all the experiments that you have created.
You can filter by experiment type (image, text, audio) and search
3. Create experiment I
To create the new experiment, you have to click in the "Create new experiment" button and then select the experiment type.
4. Create experiment II
Once you've selected the type of experiment, choose the task you need your model to develop.
In this example select "Image Classification"
5. Create experiment III
Then you define a name and description for your experiment. Optionally, you can upload an image (E.g. company logo) for your experiment
6. Create experiment IV
Now, it’s time to upload the data (images) that will be used to teach the platform the main patterns about the problem you want to solve.
You can download the dataset we used clicking here: Momo Challenge Dataset
Just drag & drop a zip file with the images organized into folders (if you had more categories in your use case then just create one folder per category)
7. Create experiment V
In the last step, if you are an expert user, you can optionally modify the default experiment’s configuration. If the default configuration is used, the platform will use the best candidate models for your experiment type.
Congrats! You have completed all the required steps to create the experiment: you have defined your problem and provided the data. You’ve finished! just shortly wait until the platform finds the best solution (model) for your problem!
8. Experiment page
Once the experiment is finished, in the experiment page, you will find the best model that the platform have built for your problem
If you want, you can go to the Dataset tab, and see some stats about your data. We keep your dataset for 30 days in case you want to do changes and upload a new version (this could be helpful in case the results are not good)
You can test it directly in the browser by clicking the “Use this model” button.
You also can see other trained models by clicking the “Try another model” button.
And that’s all! you have a ready to use service for recognizing is Momo is present or not in an image with 97% accuracy!
9. Test the model page
In the test page you can upload any image and try the model’s result immediately. And last but not least! you can get the required code to** integrate the model** to your project or app!
10. Let's recap
In this quick introduction to Cogniflow you have learned:
How to use Cogniflow for Image Recognition
The main steps:
Define your problem (image based)
Upload your data (images organized by folders)
Wait until an AI model for your problem is ready
Check results and test the model in the browser
Use the model through the Predict API endpoint
Visit cogniflow.ai for more insights!
Updated on: 25/05/2022