TensorRT YOLO v6.4.0 - Release Notes

What's Changed

• feat(nndeploy): adapt TensorRT-YOLO for nndeploy workflow by @laugh12321 in #249
• feat(trtyolo): add coordinate transformation methods for Box and RotatedBox by @laugh12321 in #257
• refactor(trtyolo): replace affine with letterbox and optimize mask logic by @laugh12321 in #258
• feat(trtyolo, #206): add image channel support and refactor Python bindings by @laugh12321 in #259
• refactor(trtyolo): restructure project and optimize code by @laugh12321 in #260
• refactor (examples): refactor all example code to use the new interface by @laugh12321 in #261
• feat(nndeploy): update config file to the new version by @laugh12321 in #262
• fix(trtyolo): fix conf type conversion error and add batch attribute by @laugh12321 in #263
• docs: update documentation for changes by @laugh12321 in #264
• build: update build configuration by @laugh12321 in #265
• fix(#272): prevent mask mis-alignment from out-of-bounds bbox by @laugh12321 in #273

Full Changelog: v6.3.2...v6.4.0

TensorRT YOLO v6.3.2 - Release Notes

What's Changed

• docs: update model structure images and modify README accordingly by @laugh12321 in #235
• fix(warpaffine): correct affine matrix center-shift & remove redundant ops by @laugh12321 in #237
• fix(#229): enableSwapRB ignored causing color-swap failure by @laugh12321 in #238
• build: update build configuration by @laugh12321 in #239

Full Changelog: v6.3.1...v6.3.2

TensorRT YOLO v6.3.1 - Release Notes

What's Changed

• fix: move operator<< implementations to header to fix printing failure by @laugh12321 in #230
• fix(#214): force overwrite CUDA arch list to remove default 5.2 and resolve __half ambiguity by @laugh12321 in #231
• fix(#212): switch CUDA device before inference by @laugh12321 in #232
• build: update build configuration by @laugh12321 in #233

Full Changelog: v6.3.0...v6.3.1

TensorRT YOLO v6.3.0 - Release Notes

What's Changed

• fix: correct width and height confusion by @laugh12321 in #189
• feat: Add support for data with pitch by @laugh12321 in #190
• move: move plugin code to modules/plugin by @laugh12321 in #191
• move: move python/tensorrt_yolo code to tensorrt_yolo by @laugh12321 in #192
• refactor: refactor and move deploy code to trtyolo by @laugh12321 in #193
• feat: update CMakeLists and add install, fix undefined symbol by @laugh12321 in #194
• feat: update tensorrt_yolo Python module by @laugh12321 in #195
• fix(#186): switch to class-aware NMS as the default behavior by @laugh12321 in #196
• feat: update examples code by @laugh12321 in #197
• docs: update documentation for changes by @laugh12321 in #198
• fix(#188): resolve typing compatibility issues by @laugh12321 in #199
• fix: initialize nmsIndicesOutput buffer to avoid undefined behavior by @laugh12321 in #201
• build: update the default list of supported CUDA architectures by @laugh12321 in #202
• build: update build configuration by @laugh12321 in #203
• chore: update gitignore by @laugh12321 in #204

Full Changelog: v6.2.0...v6.3.0

TensorRT YOLO v6.2.0 - Release Notes

What's Changed

• refactor: optimize export module for better maintainability by @laugh12321 in #163
• feat(#29): add support for YOLO-World by @laugh12321 in #164
• feat: add support for YOLOE by @laugh12321 in #165
• refactor: optimize Python CLI code by @laugh12321 in #166
• build: update build configuration by @laugh12321 in #167
• docs: update documentation for changes by @laugh12321 in #168

Full Changelog: v6.1.0...v6.2.0

TensorRT YOLO v6.1.0 - Release Notes

What's Changed

• docs: Update README with performance benchmarks, badges, and new features by @laugh12321 in #84
• fix(#85): Fix compilation errors on Windows by @laugh12321 in #86
• fix(#88): Fix linking deploy library failed on Windows by @laugh12321 in #89
• feat: Add 爱发电 sponsorship link to FUNDING.yml by @laugh12321 in #96
• feat(#98): support using the project as a Git submodule by @laugh12321 in #99
• docs(sponsor): add sponsorship section with supporter list and sponso… by @laugh12321 in #106
• fix(buffer.cpp): correct invalid argument at line 93 by @laugh12321 in #107
• fix(#100): Fix duplicate plugin registration for multi-model usage by @laugh12321 in #109
• fix(#113): Fix linking deploy library failed on Windows by @laugh12321 in #114
• fix: Correct pointer reference logic for option.cuda_mem by @laugh12321 in #122
• docs(course): update promotion for TensorRT & Triton deployment course by @laugh12321 in #130
• v6.1.0: Remove xmake build system, optimize CMake configuration and add YOLO12 support by @laugh12321 in #146

Full Changelog: v6.0.0...v6.1.0

TensorRT YOLO v6.0.0 - Release Notes

What's Changed

• Fix failed to build TensorRT Engine with Custom Plugins on Windows by @laugh12321 in #70
• Fix Duplicate Oriented Bounding Boxes in RotatedNMS Plugin under FP16 Precision by @laugh12321 in #72
• Corrected spelling errors in the code by @laugh12321 in #73
• Add Ultralytics Classify Support by @laugh12321 in #77
• Fixes for Documentation and Comments - Non-critical issue by @laugh12321 in #78
• Refactor tensorrt_yolo.infer module and remove deprecated typing types (Tuple, List, Set, Dict) by @laugh12321 in #79
• Major Refactor and Optimizations by @laugh12321 in #83

New Contributors

• @laugh12321 made their first contribution in #70

Full Changelog: v5.0.0...v6.0.0

TensorRT YOLO v5.0.0 - Release Notes

Breaking Changes

• Add EfficientRotatedNMS Plugin for OBB Model Inference (0caaf27)
• Add Support for YOLO OBB Export and Inference with EfficientRotatedNMS Plugin (c2686cc)
• Add Support for YOLO11 Detect and OBB Detect (01c8eb4)
• Refactor: Enable plugin compilation as a dynamic library independently of TensorRT-OSS (4506565)
• Add EfficientIdxNMS Plugin for Segmentation Model Inference (72324ed)
• feat(YOLOv10): Update detect head to reduce ONNX size (701e211)
• feat(cli): Removed YOLOv6/7/9 export options and directed to official repositories (af0783b)
• feat(Segment): Add support for exporting YOLOv3 and YOLOv5 segmentation models to ONNX using the EfficientIdxNMS Plugin (efe18ab)
• refactor: Simplify inference with templates, separate OBB, update bindings (5af55b1)
• feat(Segment): Add support YOLO Segmentation inference module with C++ and Python bindings (ee3e2f9)
• build(Dockerfile): Update to use newer base image (7cf37ee)
• feat(Segment): Add example for YOLO Segmentation (135d213)
• feat(Pose): Add support for exporting Ultralytics Pose models to ONNX using the EfficientIdxNMS Plugin (5fedc5f)
• feat(Pose): Add YOLO Pose Estimation inference module with C++ and Python bindings, include example (687b8ea)

Bug Fixes

• Fix TypeError: milliseconds(): incompatible function arguments. (931e8b1)
• Fix: Aligned precision (12ea4da)
• fix: Correct syntax error in xmake.lua (f85339a)
• fix: Fix type mismatch in YOLOv10 detect head (b2900a2)
• fix: Corrected the torch.hub.load function to use _verbose=False instead of verbose=False to properly silence the output. (9f2c52e)
• fix: Address missing imports, dependency issues, and default settings in CLI (05e6355)
• fix: Correct rgbPtr comment from BGR to RGB (9488e10)
• fix: Corrected the description of the cudaMem parameter in the comments (d712141)
• fix: Replace raise with sys.exit(1) for consistent exception handling (9316089)
• fix(#59): Resolved Custom Plugin Error with trtexec for TensorRT versions 10.0.x to 10.1.x (758da3b)
• fix: Ensure output directory creation is conditional on args.output presence (06a577c)
• fix: Resolve metadata inconsistency in onnx-simplifier package installation (1d9a7a4)
• feat(Pose): Adapt code to support 2D and 3D keypoint coordinates (7922d89)

Full Changelog: v4.0...v5.0.0

TensorRT YOLO v4.0 - Release Notes

Breaking Changes

• Add Dockerfile for building project Docker image (73060db)
• Add support for YOLOv3 and Ultralytics model export (8f2af94)
• Added Support for YOLOv10 (62071cb)
• Refactor deploy library (8a4df33)
• Use CUDA Graph to Accelerate Static Model Inference (3576c78)
• Refactor: Add BaseDet base class, refactor DeployDet and DeployCGDet (416e77b)
• Add streaming video support using VideoPipe (#17, #19)
• feat: major update with pybind11 integration and new 4.0 tag (3244eea)

Bug Fixes

• Fix incorrect time interval calculation (a3dee2a)
• Fix: Include <cstring> to resolve "memcpy is not a member of std" error in Linux (1b763d9)
• Update detection output variable names for clarity (fe67b01)
• Add cstdint to resolve Linux compilation issue (f602dc4)
• Fix: Graph input and output tensors must include dtype information. (2cacb7d)

Full Changelog: v3.0...v4.0

TensorRT YOLO v3.0 - Release Notes

Breaking Changes

• Add TensorRT INT8 PTQ support (87f67ff)
• Add C++ inference implementation (0f3069f)
• Implemented parallel preprocessing with multiple streams (86d6175)
• Refactor C++ inference code to support dynamic and static libraries (425a1a4)
• Refactored Python code related to TensorRT-YOLO and packaged it as tensorrt_yolo. (a10ebc8)

Bug Fixes

• Fix batch visualize bug (9125219)
• Remove deleted move constructor and move assignment operator (e287342)
• Fix duplicate imports (1237e21)
• Fix bug (24ea950)

Full Changelog: v2.0...v3.0