Henry Hyeonmok Ko's repositories
Deep_Sea-NN
Enhancing underwater images using a truncated U-Net architecture for real-time color correction applications
CAPTCHA_v4
Why are CAPTCHAs so hard? Today's CAPTCHA is easily breakable by bots while being rather difficult for humans. We present CAPTCHAv4: an algorithm which relies on latent space mappings and Stable Diffusion to generate a new paradigm of CAPTCHA images.
diffusion_deepdive
exploration-based project for gaining a deeper understanding of diffusion models
autoencoder_experimenting
mnist with autoencoders/ basic experimenting
bjc-r
The Beauty and Joy of Computing public resource repository.
Bunny
A family of lightweight multimodal models.
cuda-mode
Learning CUDA. This repo includes all scratchwork from many resources.
VLM_interpretability
Exploring how Vision-Language models interpret text in images
contrastive-unpaired-translation
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)
DCGAN_Experiments
MNIST with DCGAN
evogym
A large-scale benchmark for co-optimizing the design and control of soft robots, as seen in NeurIPS 2021.
gan_experimenting
vanilla gans. what are thoseee
henryhmko.github.io
personal website
NNs_from_Scratch
Only using numpy to create different NNs. This is more for me understanding how things work under the hood
Personal_Encryption_Method_PUBLIC
My own encryption method using prime numbers, dictionaries, and factoring.
pytorch-ssim
pytorch structural similarity (SSIM) loss