yuanmu97/InFi
InFi is a library for building input filters for resource-efficient inference.
Deploying machine learning models in real-world applications often requires significant computational power. This project helps you reduce the resources needed for tasks like speech recognition or object detection by intelligently filtering out easy-to-classify inputs. It takes your pre-processed audio spectrograms or video frames and provides a filter that determines which inputs require full model processing, saving computational resources.
No commits in the last 6 months.
Use this if you are deploying trained machine learning models for tasks such as speech processing, image classification, or object detection and need to optimize their performance and reduce computational costs, especially in mobile or edge environments.
Not ideal if your primary goal is to improve the raw accuracy of your model or if your inference environment has unlimited computational resources.
Stars
41
Forks
8
Language
Python
License
MIT
Category
Last pushed
Oct 25, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yuanmu97/InFi"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
microsoft/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
onnx/onnx
Open standard for machine learning interoperability
PINTO0309/onnx2tf
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The...
NVIDIA/TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This...
onnx/onnxmltools
ONNXMLTools enables conversion of models to ONNX