dnth / yolov5-deepsparse-blogpost
By the end of this post, you will learn how to: Train a SOTA YOLOv5 model on your own data. Sparsify the model using SparseML quantization aware training, sparse transfer learning, and one-shot quantization. Export the sparsified model and run it using the DeepSparse engine at insane speeds. P/S: The end result - YOLOv5 on CPU at 180+ FPS using…
☆56Updated last year
Alternatives and similar repositories for yolov5-deepsparse-blogpost:
Users that are interested in yolov5-deepsparse-blogpost are comparing it to the libraries listed below
- Yolov5 TensorRT Implementations☆67Updated 2 years ago
- Computer Vision deployment tools for dummies and experts. CVU aims at making CV pipelines easier to build and consistent around platform…☆88Updated last year
- yolov5, yolov8, segmenations, face, pose, keypoints on deepstream☆96Updated last year
- ☆53Updated 3 years ago
- Implementation for the paper 'YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs'☆95Updated last year
- ☆53Updated 3 years ago
- Deepstream app use retinaface and arcface for face recognition.☆62Updated 6 months ago
- Deepstream face detection & recognition☆22Updated 2 years ago
- NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 implementation for YOLO-Segmentation models☆58Updated last year
- NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 application for YOLO-Face models☆65Updated last year
- A lightweight vision library for performing large scale object detection & instance segmentation☆54Updated last year
- Exporting YOLOv5 for CPU inference with ONNX and OpenVINO☆37Updated 7 months ago
- This repository serves as an example of deploying the YOLO models on Triton Server for performance and testing purposes☆59Updated 10 months ago
- Use Deepstream python API to extract the model output tensor and customize the post-processing of YOLO-Pose☆61Updated last year
- Provides an ensemble model to deploy a YoloV8 ONNX model to Triton☆35Updated last year
- Quantization Aware Training☆67Updated last year
- Python scripts performing object detection using the YOLOv6 model in ONNX.☆94Updated 2 years ago
- YOLOv7 training. Generates a head-only dataset in YOLO format. The labels included in the CrowdHuman dataset are Head and FullBody, but i…☆29Updated 9 months ago
- A project demonstrating how to use nvmetamux to run multiple models in parallel.☆99Updated 5 months ago
- Python Implementation for Performing Object Detection Using YOLOv9 with ONNX & ONNXRuntime☆48Updated last year
- Implementation of YOLOv9 QAT optimized for deployment on TensorRT platforms.☆105Updated last month
- Python version for NVIDIA Deepstream's LPR. https://developer.nvidia.com/blog/creating-a-real-time-license-plate-detection-and-recognitio…☆34Updated 4 years ago
- ☆80Updated 3 years ago
- 🔖🔄 | YOLO to VOC format <> VOC to YOLO format | Multiprocessing support☆37Updated 4 months ago
- YOLOv4 accelerated wtih TensorRT and multi-stream input using Deepstream☆36Updated 3 years ago
- NVIDIA Deepstream 6.1 Python boilerplate☆138Updated last year
- Python scripts performing object detection using the YOLOv7 model in ONNX.☆206Updated 2 years ago
- PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment. We optimize on the basis of the p…☆30Updated 3 weeks ago
- Face Recognition with RetinaFace and ArcFace.☆81Updated 2 years ago
- ☆55Updated last year