monkbai/DNN-decompiler
BTD - Bin To DNN: A DNN Executables Decompiler
This project helps security researchers and reverse engineers understand how compiled Deep Neural Network (DNN) executables work on x86 CPUs. It takes a DNN executable as input and outputs a detailed model specification, including operator types, network topology, dimensions, and parameters. This is useful for analyzing proprietary models or understanding compiler optimizations, especially for those working with compiled AI/ML systems.
200 stars.
Use this if you need to reverse-engineer a compiled Deep Neural Network application running on x86 to understand its structure, operators, and parameters.
Not ideal if you are a data scientist primarily working with high-level AI/ML frameworks like TensorFlow or PyTorch and don't need to analyze compiled binaries.
Stars
200
Forks
5
Language
Python
License
—
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/monkbai/DNN-decompiler"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pymc-devs/pytensor
PyTensor allows you to define, optimize, and efficiently evaluate mathematical expressions...
arogozhnikov/einops
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
lava-nc/lava-dl
Deep Learning library for Lava
tensorly/tensorly
TensorLy: Tensor Learning in Python.
tensorpack/tensorpack
A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility