Add Shiquan as co-authors for great contributions on TRT (#258)

* Update README in deployment/tensorrt

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Add Shiquan as co-authors for great contributions on TRT

* Update TensorRT statement

* Update badges

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

README.md

@@ -24,9 +24,9 @@ ______________________________________________________________________
 [![pre-commit.ci status](https://results.pre-commit.ci/badge/github/zhiqwang/yolov5-rt-stack/main.svg)](https://results.pre-commit.ci/latest/github/zhiqwang/yolov5-rt-stack/main)
 
 [![codecov](https://codecov.io/gh/zhiqwang/yolov5-rt-stack/branch/main/graph/badge.svg?token=1GX96EA72Y)](https://codecov.io/gh/zhiqwang/yolov5-rt-stack)
-[![license](https://img.shields.io/github/license/zhiqwang/yolov5-rt-stack?color=brightgreen)](LICENSE)
-[![Slack](https://img.shields.io/badge/slack-chat-green.svg?logo=slack)](https://join.slack.com/t/yolort/shared_invite/zt-mqwc7235-940aAh8IaKYeWclrJx10SA)
-[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](https://github.com/zhiqwang/yolov5-rt-stack/issues?q=is%3Aopen+is%3Aissue+label%3A%22help+wanted%22)
+[![license](https://img.shields.io/github/license/zhiqwang/yolov5-rt-stack?color=dfd)](LICENSE)
+[![Slack](https://img.shields.io/badge/slack-chat-aff.svg?logo=slack)](https://join.slack.com/t/yolort/shared_invite/zt-mqwc7235-940aAh8IaKYeWclrJx10SA)
+[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-pink.svg)](https://github.com/zhiqwang/yolov5-rt-stack/issues?q=is%3Aopen+is%3Aissue+label%3A%22help+wanted%22)
 
 ______________________________________________________________________
 
@@ -46,7 +46,9 @@ ______________________________________________________________________
 
 ## 🆕 What's New
 
-- *Sep. 24, 2021*. Add `ONNXRuntime` C++ interface example. Thanks to [itsnine](https://github.com/itsnine).
+- *Dec. 27, 2021*. Add `TensorRT` C++ interface example. Thanks to [Shiquan](https://github.com/ShiquanYu).
+- *Dec. 25, 2021*. Support exporting to `TensorRT`, and inferencing with `TensorRT` Python interface.
+- *Sep. 24, 2021*. Add `ONNXRuntime` C++ interface example. Thanks to [Fidan](https://github.com/itsnine).
 - *Feb. 5, 2021*. Add `TVM` compile and inference notebooks.
 - *Nov. 21, 2020*. Add graph visualization tools.
 - *Nov. 17, 2020*. Support exporting to `ONNX`, and inferencing with `ONNXRuntime` Python interface.
@@ -135,6 +137,10 @@ We provide a [notebook](notebooks/inference-pytorch-export-libtorch.ipynb) to de
 
 On the `ONNXRuntime` front you can use the [C++ example](deployment/onnxruntime), and we also provide a tutorial [export-onnx-inference-onnxruntime](notebooks/export-onnx-inference-onnxruntime.ipynb) for using the `ONNXRuntime`.
 
+### Inference on TensorRT backend
+
+On the `TensorRT` front you can use the [C++ example](deployment/tensorrt), and we also provide a tutorial [onnx-graphsurgeon-inference-tensorrt](notebooks/onnx-graphsurgeon-inference-tensorrt.ipynb) for using the `TensorRT`.
+
 ## 🎨 Model Graph Visualization
 
 Now, `yolort` can draw the model graph directly, checkout our [model-graph-visualization](notebooks/model-graph-visualization.ipynb) notebook to see how to use and visualize the model graph.
@@ -152,7 +158,7 @@ If you use yolort in your publication, please cite it by using the following Bib
 
 ```bibtex
 @Misc{yolort2021,
-  author =       {Zhiqiang Wang, Fidan Kharrasov},
+  author =       {Zhiqiang Wang, Shiquan Yu, Fidan Kharrasov},
   title =        {yolort: A runtime stack for object detection on specialized accelerators},
   howpublished = {\url{https://github.com/zhiqwang/yolov5-rt-stack}},
   year =         {2021}

deployment/tensorrt/README.md

@@ -1,33 +1,79 @@
 # TensorRT Inference
 
-The TensorRT inference for `yolort`, support GPU only.
+The TensorRT inference for `yolort`, support CUDA only.
 
 ## Dependencies
 
-- TensorRT 8.x
+- TensorRT 8.0 +
 
 ## Usage
 
 1. Create build director and cmake config.
 
    ```bash
    mkdir -p build/ && cd build/
-   cmake .. -DTENSORRT_DIR=${your_trt_install_director}
+   cmake .. -DTENSORRT_DIR={path/to/your/trt/install/director}
    ```
 
 1. Build project
 
    ```bash
-   make
+   cmake --build . -j4
    ```
 
-1. Export your custom model to ONNX(see [onnx-graphsurgeon-inference-tensorrt](https://github.com/zhiqwang/yolov5-rt-stack/blob/main/notebooks/onnx-graphsurgeon-inference-tensorrt.ipynb)).
+1. Export your custom model to ONNX
+
+   Here is a small demo to surgeon the YOLOv5 ONNX model and then export to TensorRT engine. For details see out our [tutorial for deploying yolort on TensorRT](https://zhiqwang.com/yolov5-rt-stack/notebooks/onnx-graphsurgeon-inference-tensorrt.html).
+
+   - Set the super parameters
+
+     ```python
+     model_path = "https://github.com/ultralytics/yolov5/releases/download/v6.0/yolov5n6.pt"
+     checkpoint_path = attempt_download(model_path)
+     onnx_path = "yolov5n6.onnx"
+     engine_path = "yolov5n6.engine"
+
+     score_thresh = 0.4
+     iou_thresh = 0.45
+     detections_per_img = 100
+     ```
+
+   - Surgeon the yolov5 ONNX models
+
+     ```python
+     from yolort.runtime.yolo_graphsurgeon import YOLOGraphSurgeon
+
+     yolo_gs = YOLOGraphSurgeon(
+         checkpoint_path,
+         version="r6.0",
+         enable_dynamic=False,
+     )
+
+     yolo_gs.register_nms(
+         score_thresh=score_thresh,
+         nms_thresh=iou_thresh,
+         detections_per_img=detections_per_img,
+     )
+
+     # Export the ONNX model
+     yolo_gs.save(onnx_path)
+     ```
+
+   - Build the TensorRT engine
+
+     ```python
+     from yolort.runtime.trt_helper import EngineBuilder
+
+     engine_builder = EngineBuilder()
+     engine_builder.create_network(onnx_path)
+     engine_builder.create_engine(engine_path, precision="fp32")
+     ```
 
 1. Now, you can infer your own images.
 
    ```bash
    ./yolort_trt [--image ../../../test/assets/zidane.jpg]
-                 [--model_path ../../../notebooks/yolov5s.onnx]
-                 [--class_names ../../../notebooks/assets/coco.names]
-                 [--fp16]  # Enable it if your GPU support fp16 inference
+                [--model_path ../../../notebooks/yolov5s.onnx]
+                [--class_names ../../../notebooks/assets/coco.names]
+                [--fp16]  # Enable it if your GPU support fp16 inference
    ```