CactusQ/tensor_rt_for_beginners
Beginner-friendly introduction to TensorRT using Torch-TRT on YOLO-V5
This helps deep learning engineers accelerate the performance of their object detection models. By taking a trained YOLO-V5 PyTorch model and a dataset of images, it outputs a significantly faster model ready for deployment, along with a comparison of inference speeds. It's ideal for engineers working on real-time object detection applications.
No commits in the last 6 months.
Use this if you need to deploy YOLO-V5 object detection models with the fastest possible inference speeds on NVIDIA GPUs.
Not ideal if you are working with non-YOLO-V5 models, or if you don't have access to an NVIDIA GPU.
Stars
12
Forks
6
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 07, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CactusQ/tensor_rt_for_beginners"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ultralytics/yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
ultralytics/yolov3
YOLOv3 in PyTorch > ONNX > CoreML > TFLite
mindspore-lab/mindyolo
A toolbox of yolo models and algorithms based on MindSpore
ultralytics/assets
Ultralytics assets
stephanecharette/DarkHelp
C++ wrapper library for Darknet