Overview

An image classifier is a type of artificial intelligence (AI) system designed to recognize and categorize images into predefined classes or categories. This system uses machine learning algorithms, particularly deep learning techniques like convolutional neural networks (CNNs), to analyze and interpret visual data. 

Image classifier can be trained on large datasets of labeled images, where each image is associated with a specific class or category. During training, the algorithm learns to extract features from the images and make predictions based on those features. Once trained, the classifier can then be used to classify new, unseen images into the learned categories. 

Documentation

Features and Limitations: 

Precise image classification by reliably identifying images according to predefined classes with exceptional accuracy. 

Image classifier can be trained to recognize a wide range of objects, patterns, and concepts, making them applicable to diverse use cases. 

image classifier heavily relies on the quality and quantity of labeled training data. Insufficient or biased training data can lead to poor classification accuracy and generalization. 

Dependencies: 

Ensure You Install the following components (from Mendix Marketplace) before using this module. 

• Community Commons 

Configuration: 

Train your ML model with Custom Dataset and Classes. 

You can get the model from here GitHub 

Save your dataset in your files (refer screenshot1) in the similar manner 

Change the Following in the Python code: 

In line10 change this code with the path where your dataset files are stored 

DIR =r"Place your path here" Eg-r"C:/users/doc/” 

In line11 change the categories with your custom categories name which should match with file names in above step 

CATEGORIES = ["airplane","automobile","bird","cat","deer","dog","frog","horse","ship","truck"] 

In line72 change the path where you want to save the model 

Pathtosave=r"Change your path here" 

Install the module and required dependencies. 

In ML_model_mapping Import the model which is saved from the ML model You can find it in your files. 

Configure the tensor shapes (refer Screenshot2) to solve the errors. 

Change the microflow in CallMLmodel activity with the objects of created entities 

Create Classes with their respective indexes Matching the above Categories (refer screenshot3) in the app before Calling the ML model.