chenliu-1996 / simulatebiggerbatchsize

We provide a simple code snippet on how to simulate a bigger batch size when it is not directly achievable by your GPU.

Greetings from Chen!

Hi, I am Chen Liu, a PhD student in Computer Science at Yale University.

I work on machine learning in healthcare. Lately I am diving into understanding the neural network manifold.

I am generally over-booked on projects, but feel free to reach out for collaboration.

Recent repositories

✔️ [ICML 2023 Workshop on TAG-ML] A novel method to compute entropy and mutual information in neural net representations

✔️ An on-the-fly evaluator for GANs, with a simple working example of DCGAN on SVHN

✔️ A framework for multi-granular unsupervised medical image segmentation

✔️ A guide to simulate bigger batch sizes beyond GPU capability

Technical Blogs

✔️ A Technical Deep Dive into Drag Your GAN (DragGAN)

Course Projects

✔️ Towards a Large-Scale Unbiased Machine Learning Benchmark for Cell Instance Segmentation: Final Report for CPSC 537 Intro to Database Systems

Contact information

• Personal Website
• LinkedIn
• Lab Website

Resume

https://chenliu-1996.github.io/CV/ChenLiu_resume.pdf