apple/ml-upscale
Export utility for unconstrained channel pruned models
This tool helps machine learning engineers and researchers optimize deep learning models, specifically for computer vision tasks. It takes an existing PyTorch image classification model, analyzes its structure, and intelligently removes unnecessary parts (channels) to make it smaller and faster. The result is a more efficient model that maintains high accuracy, suitable for deployment in performance-critical applications.
No commits in the last 6 months.
Use this if you need to significantly reduce the size and improve the inference speed of your PyTorch image classification models without sacrificing accuracy.
Not ideal if you are not working with PyTorch models or if your primary concern is not model size and inference speed optimization.
Stars
71
Forks
11
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 14, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/apple/ml-upscale"
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
google/qkeras
QKeras: a quantization deep learning library for Tensorflow Keras
fastmachinelearning/qonnx
QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
tensorflow/model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization...