LearningByDoing Series: Understanding effects of activation functions

Ablation study: Activation functions Goal here is to observ or record changes in accuracy, loss, or other performance indicators. Activation Functions under consideration Sigmoid Tanh ReLU LeakyReLU ELU SELU Softplus Mish GELU Swish We are using ResNet-18 model wit... Read more 27 Feb 2024 - 12 minute read

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

Older Newer