#371 · Primary category: Computer Vision
quiver
Interactive convnet features visualization for Keras
Project last updated:09/04/20
GitHub Stars
1.8K
Forks
224
Contributors
11
License
MIT
Why we included this project
Quiver gives you a visual look inside a trained Keras convolutional network. You launch a local web dashboard with your model, feed it images, and it shows the activation maps and top predictions for every layer, so you can actually watch what each filter responds to. That makes it handy for debugging misclassifications or explaining convnet internals to students, because you see the failure modes instead of just staring at accuracy numbers. Setup is minimal: one line of code starts the server, and you can pass class labels and an input folder. It doesn't replace Keras; it sits alongside it and works with whatever model you already have.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)