poloclub/interactive-classification
Interactive Classification for Deep Learning Interpretation
This tool helps researchers and practitioners understand how deep learning image classifiers make decisions. You provide an image, and the system shows you what parts of the image the model focuses on for classification. You can also edit areas of the image to see how it impacts the model's prediction, helping you explore its robustness and sensitivity.
No commits in the last 6 months.
Use this if you need to debug why an image classifier made a specific prediction or want to test how sensitive your model is to changes in an image.
Not ideal if you're looking for a tool to train new deep learning models or perform large-scale image classification tasks.
Stars
79
Forks
17
Language
JavaScript
License
MIT
Category
Last pushed
Jan 25, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/poloclub/interactive-classification"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ndif-team/nnsight
The nnsight package enables interpreting and manipulating the internals of deep learned models.
huggingface/dataset-viewer
Backend that powers the dataset viewer on Hugging Face dataset pages through a public API.
LYH-YF/MWPToolkit
MWPToolkit is an open-source framework for math word problem(MWP) solvers.
epfml/disco
DISCO is a code-free and installation-free browser platform that allows any non-technical user...
ndif-team/ndif
The NDIF server, which performs deep inference and serves nnsight requests remotely