Techno Blender
Digitally Yours.
Browsing Tag

Gur

CLIP: Creating Image Classifiers Without Data | by Lihi Gur Arie, PhD | Feb, 2023

A hands-on tutorial explaining how to generate a custom Zero-Shot image classifier without training, using a pre-trained CLIP model. Full code included.Image generated by the author with MidjourneyImagine you need to classify whether people wear glasses, but you have no data or resources to train a custom model. In this tutorial, you will learn how to use a pre-trained CLIP model to create a custom classifier without any training required. This approach is known as Zero-Shot image classification, and it enables…

Enhancing the Robustness of Image Classification Models with AugMix | by Lihi Gur Arie, PhD | Dec, 2022

Adding Consistency Loss between AugMix Augmented Images to enhance the Generalization of your Image Classification ModelFigure 1 - Visualizing AugMix: Original Image (left) and Two Augmented Versions. | Image by authorIntroductionImage classification models are best able to predict data from the same distribution as the training data. However, in real-world scenarios, the input data may suffer from variations. When inferencing with different cameras for example, the lighting conditions, contrast, color distortions etc.…

Color Segmentation with K-means Clustering | by Lihi Gur Arie, PhD | Dec, 2022

A detailed guide to identify and quantify objects in an image based on their color, using Contours and K-means clustering.IntroductionColor segmentation is a technique used in computer vision to identify and distinguish different objects or regions in an image based on their colors. Clustering algorithms can automatically group similar colors together, without the need to specify threshold values for each color. This can be useful when working with images that have a large range of colors, or when the exact threshold…