zanvari/resnet50-quantization
Resnet50 Quantization for Inference Speedup in PyTorch
This helps deep learning practitioners make their ResNet50 image recognition models run much faster on common hardware without significant loss of accuracy. By taking an existing ResNet50 model and a small sample of representative data, it produces a new, optimized model that uses less memory and computes predictions twice as fast. This is for machine learning engineers and researchers deploying image classification models.
No commits in the last 6 months.
Use this if you need to speed up the inference time of your ResNet50-based image classification models while minimizing memory usage and maintaining accuracy.
Not ideal if your application requires extremely high precision from your neural network or if you are not working with a ResNet50 architecture.
Stars
22
Forks
2
Language
Jupyter Notebook
License
—
Category
Last pushed
Jan 30, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zanvari/resnet50-quantization"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
open-mmlab/mmengine
OpenMMLab Foundational Library for Training Deep Learning Models
Xilinx/brevitas
Brevitas: neural network quantization in PyTorch
fastmachinelearning/qonnx
QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
google/qkeras
QKeras: a quantization deep learning library for Tensorflow Keras
tensorflow/model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization...