Files
FastDeploy/examples/vision/detection/yolov7/quantize/cpp/README.md
2022-11-10 19:11:24 +08:00

37 lines
1.6 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# YOLOv7量化模型 C++部署示例
本目录下提供的`infer.cc`,可以帮助用户快速完成YOLOv7量化模型在CPU/GPU上的部署推理加速.
## 部署准备
### FastDeploy环境准备
- 1. 软硬件环境满足要求,参考[FastDeploy环境要求](../../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
- 2. FastDeploy Python whl包安装参考[FastDeploy Python安装](../../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
### 量化模型准备
- 1. 用户可以直接使用由FastDeploy提供的量化模型进行部署.
- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../../../../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署.
## 以量化后的YOLOv7模型为例, 进行部署
在本目录执行如下命令即可完成编译,以及量化模型部署.
```bash
mkdir build
cd build
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-0.6.0.tgz
tar xvf fastdeploy-linux-x64-0.6.0.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.6.0
make -j
#下载FastDeloy提供的yolov7量化模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar
tar -xvf yolov7_quant.tar
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
# 在CPU上使用Paddle-Inference推理量化模型
./infer_demo yolov7_quant 000000014439.jpg 0
# 在GPU上使用TensorRT推理量化模型
./infer_demo yolov7_quant 000000014439.jpg 1
# 在GPU上使用Paddle-TensorRT推理量化模型
./infer_demo yolov7_quant 000000014439.jpg 2
```