AMAR POTDAR Thoughts, Experiences, Projects
CNN Series:0
In this series, we’ll dive into the realm of CNNs, a groundbreaking class of neural networks designed to process visual data. From image recognition and object detection to semantic segmentation and beyond, CNNs have revolutionized the field of computer vision and paved the way for incredible advancements in artificial intelligence. Read more 20 May 2023 - less than 1 minute read
CNN Series: LeNet
Paper Gradient-Based Learning Applied to Document Recognition Authors: Yann LeCun, Leon Bottou, Yoshua Bengio, and Patrick Haffner LeNet: LeNet-5 is a pioneering convolutional neural network (CNN) that played a foundational role in the field of deep learning, particularly in the application of using deep learning to image recognition ... Read more 17 May 2023 - less than 1 minute read
BYTE: Simple and Effective association method
Introduction Following are my notes on BYTE, simple and effective association method. Proposed in paper ByteTrack: Multi-Object Tracking by Associating Every Detection Box. BYTE, The Algo? For each frame in the video, we predict the detection boxes and scores using the detector Det. We separate all the detection boxes Dboxes into two par... Read more 15 May 2023 - 1 minute read