Many people employ expensive GPUs to reduce the training and inference times for machine learning on industrial datasets that keep growing. The presentation of our project will show how you may use Intel's optimised libraries, which are both inexpensive and streamlined, to speed up your machine learning process.
This reference notebook will demonstrate how to leverage several accelerated Python libraries found in the Intel® AI Analytics Toolkit to increase the speed, accuracy, and throughput of your machine learning (ML) process. In this notebook, the primary libraries we'll utilise are:
1.Intel® Distribution of Modin*
2.Intel® Extension for Scikit-learn*
3.Intel® Open Vino Toolkit
4.Intel® Extension for Pytorch
5.Intel®Optimization for Tensorflow
Yolo, a convolutional neural network-based technique, is used in our project Detectify to detect objects. What makes object detection great, then? A detection algorithm, in contrast to a recognition algorithm, not only anticipates class labels but also locates objects.
After getting selected in this prototype round , we would be deploying an app in which users can input an image and object detection is done by the app itself.We will also apply the same algorithm to video detections and objects are detected in the video
If intel members keep our hardwork in mind and select us,We would be deploying an useful object detection app using Intel Optimized Libraries.
After getting selected in prototype round,we will enable video processing in which objects are detected in a live video Our github code:-(https://https://github.com/MohamedFarhun/IntelOneAPI2023Hack2skill-Detectify)