User Review
( votes)
Introduction:
With the growth in technology we have seen an incline towards the technologies related to Machine Learning and Artificial Intelligence in our day-to-day life. In recent few years Microsoft has been pushing Low-Code/ No-Code ideology and have been incorporating ML and AI technologies in their PCF control, AI Builder Models, etc. Evidence of this can be seen in the recent PCF control like Business card Scanner, Document Automation models, etc.
In this blog series, we will be seeing the Image classification model by Lobe which is currently in preview.
Microsoft Lobe is a free desktop application provided by Microsoft which can be used to classify Images into labels. This model can also be used in different ways, for e.g., it can be added in Canvas Apps, Power Automate.
The overview of creating an Image Classification model is given below:
- Creating a model
- Providing sample data
- Training the model
- Evaluating and correcting the model detection
- Testing the model
- Using the model
To get started with creating an Image Classification model using Microsoft Lobe please follow the steps given below:
- Download and Install the Microsoft Lobe Desktop application from here.
- Once the download is finished, open the Microsoft Lobe Desktop application, and then click on Create Project
- Give the project an appropriate name in the top-left corner and for the sample dataset you can choose between Saved Images, Camera, and Dataset.
- In this example, we will create an attire detection model which will detect if an employee is wearing Casual or Formal attire. Here we will provide the model with some data and will label the Image based on which they would be classified.
- Once done the Lobe will train the Model. And if there are any incorrect detection then you can correct them by changing the image label to an adequate label.
- You can try out the model in real-time by clicking on the Use
Note: For high accuracy, the sample data should be high and diverse which will result in better training of the model.
Conclusion:
In this blog, we have seen how easy it is to create an Image detection model without writing a single line of code.
