xiaochus/DeepModelDeploy
Deploy deep learning model on difference hardware and framework. (TensorRT/ONNX/MNN/RKNN)
This project helps machine learning engineers and embedded systems developers take their trained deep learning models and run them efficiently on various specialized hardware. You provide your deep learning model, and it outputs a version optimized for specific deployment targets, like NVIDIA GPUs or ARM-based NPUs. This is for professionals who need to move models from development to production on edge devices or specialized hardware.
No commits in the last 6 months.
Use this if you need to deploy deep learning models onto a range of hardware, including specialized chips like NPUs or embedded GPUs, and want to optimize their performance for these targets.
Not ideal if you are only running deep learning models on standard cloud servers or desktop PCs and don't require hardware-specific optimizations.
Stars
13
Forks
2
Language
C++
License
MIT
Category
Last pushed
Jan 02, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/xiaochus/DeepModelDeploy"
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