NoahVl/Explaining-In-Style-Reproducibility-Study
Re-implementation of the StylEx paper, training a GAN to explain a classifier in StyleSpace, paper by Lang et al. (2021).
This project helps machine learning researchers understand why an image classifier makes specific decisions. By inputting a trained image classifier and a dataset of images, it generates visual explanations in the form of modified images, showing which visual features (like hair color or facial expression) influence the classifier's output. This is useful for researchers who need to interpret and validate the behavior of their AI models.
No commits in the last 6 months.
Use this if you are a machine learning researcher who needs to visually understand the decision-making process of your image classification models.
Not ideal if you are looking for a tool to directly improve classifier accuracy or for non-image-based machine learning interpretability.
Stars
38
Forks
8
Language
Jupyter Notebook
License
—
Category
Last pushed
Dec 02, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/NoahVl/Explaining-In-Style-Reproducibility-Study"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sanjay035/Sketch2Color-anime-translation
Given a simple anime line-art sketch the model outputs a decent colored anime image using...
cgao96/deepsketch2face
Demo and Database of "DeepSketch2Face" (SIGGRAPH 2017)
thaoshibe/BeautyGAN-PyTorch-reimplementation
A re-implementation of BeautyGAN: Instance-level Facial Makeup Transfer with Deep Generative...
LingDong-/edges2calligraphy
Using pix2pix to convert scribbles to Chinese calligraphy
vinesmsuic/White-box-Cartoonization-PyTorch
PyTorch implementation of “Learning to Cartoonize Using White-box Cartoon Representations” (CVPR...