Skip to content

TensorRT YOLO v1.0 - Release Notes
Compare
Choose a tag to compare
@laugh12321 laugh12321 released this 28 Feb 13:35
· 210 commits to main since this release
v1.0
cdb5c35

Breaking Changes

  • Supports FLOAT32, FLOAT16 ONNX export, and TensorRT inference
  • Supports YOLOv5, YOLOv8, PP-YOLOE, and PP-YOLOE+
  • Integrates EfficientNMS TensorRT plugin for accelerated post-processing
  • Utilizes CUDA kernel functions to accelerate preprocessing
  • Supports Python inference

Bug Fixes

  • Fix pycuda.driver.CompileError on Jetson (#1)
  • Fix Engine Deserialization Failed using YOLOv8 Exported Engine (#2)
  • Fix Precision Anomalies in YOLOv8 FP16 Engine (#3)
  • Fix YOLOv8 EfficientNMS output shape abnormality (0e542ee)
  • Fix trtexec Conversion Failure for YOLOv5 and YOLOv8 ONNX Models on Linux) (#4)
  • Fix Inference Anomaly Caused by preprocess.cu on Linux (#5)

Full Changelog: https://github.com/laugh12321/TensorRT-YOLO/commits/v1.0

Assets 2
Loading