jdhao / master_thesis

This repo is created to host my master thesis

I am a machine learning engineer who is passionate about solving real-world problems using machine learning algorithms. I am experienced in image processing using OpenCV and PIL, and also in data visualization using Matplotlib. I have been working on various vision-related projects, ranging from image retrieval, OCR, document image analysis and reconstruction, to video fingerprinting/deduplication.

I am also a FOSS lover and a Vim/Nvim enthusiast in particular, sharing tips and tricks on using Neovim. More info about me can be found on my website: https://jdhao.github.io/.

Languages and tools

Projects

• I am maintaining nvim-config -- A modern Neovim configuration with full battery for Python, C++, Markdown, LaTeX, and more...
• Author of better-escape.vim -- a Vim/Neovim plugin that helps the users escape insert mode without lagging.
• Author of whitespace.nvim -- A nvim plugin to show and trim trailing white spaces.
• minimal_vim -- A minimal Vim/Nvim configuration in just one file without external dependencies.
• deep firearm: Using a Siamese network with double margin contrastive loss for fine-grained gun image retrieval.

Latest blog posts

• 家常煎羊排制作
• 凉拌茄子制作
• Configure Python logging with dictConfig
• Debugging Wezterm Issues
• Black Formatter Setup for Python Project

Stack Overflow and GitHub stats

Random quotes

master_thesis's Issues

Thesis English version

Do you have English version of your thesis? I have same problem with you. My dataset contain many image with different size, many orientation,.. like firearm.

Also I'm using Pytorch with batch size = 1 (I have SPP layer in network), forward one image at time. So my training time is very slow. Do you have any suggestion?

Sorry for my bad English.