This training program was specifically designed to dive deep into the fascinating field of Computer Vision. Throughout the training, participants had the opportunity to explore various aspects of Computer Vision, with a strong focus on building deep neural networks and convolutional neural networks (CNNs) from scratch.One of the highlights of the training was the demonstration of pretrained models such as Mask R-CNN, YOLOv8 and SAM. By showcasing their implementation, we showcased the incredible advancements for those models in object detection and segmentation tasks.