ML

Seq2seq Model with Attention

Digested and reproduced from Visualizing A Neural Machine Translation Model by Jay Alammar. Table of Contents 1. Architecture of Seq2seq 2. Attention Mechanism Sequence-to-sequence models are deep learning models that have achieved a lot of success in tasks like machine translation, text summarization, and image captioning.

Handuo

Jun 1, 2020 7 min read Deep Learning Basics

You only look once (YOLO) -- (2)

YOLO has higher localization errors and the recall (measure how good to locate all objects) is lower, compared to SSD. YOLOv2 is the second version of the YOLO with the objective of improving the accuracy significantly while making it faster.

Handuo

Aug 20, 2018 2 min read Object Detection

You only look once (YOLO) -- (2)

You only look once (YOLO) -- (1)

You Only Look Once (YOLO) is an object detection system targeted for real-time processing. There are three versions of YOLO: YOLO, YOLOv2 (and YOLO9000) and YOLOv3. For this article, we mainly focus on YOLO first stage.

Handuo

Aug 20, 2018 4 min read Object Detection

Pooling Layer in CNN (1)

Today I didn’t have the mood to continue my work on map merging of different cameras. So I read the paper from DeepMind of Learned Deformation Stability in Convolutional Neural Networks recommended by Wang Chen.

Handuo

May 2, 2018 3 min read Network architecture