hpi-xnor/BMXNet-v2
BMXNet 2: An Open-Source Binary Neural Network Implementation Based on MXNet
This tool helps researchers and deep learning engineers develop and test neural networks that use binary or low-bit precision. It takes standard neural network architectures and converts their complex layers into more efficient, binarized versions, resulting in models that are smaller and faster for deployment. It is designed for those experimenting with efficient AI on resource-constrained devices or in situations requiring rapid inference.
232 stars. No commits in the last 6 months.
Use this if you are a deep learning researcher or engineer focused on creating efficient neural networks that can run on devices with limited computational power or memory.
Not ideal if you are looking for an off-the-shelf solution for high-precision deep learning tasks or if you are not comfortable with deep learning framework modifications.
Stars
232
Forks
32
Language
C++
License
Apache-2.0
Category
Last pushed
May 20, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hpi-xnor/BMXNet-v2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
apache/tvm
Open Machine Learning Compiler Framework
uxlfoundation/oneDNN
oneAPI Deep Neural Network Library (oneDNN)
Tencent/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
OpenMined/TenSEAL
A library for doing homomorphic encryption operations on tensors
iree-org/iree-turbine
IREE's PyTorch Frontend, based on Torch Dynamo.