安装文档

# CUDA9.0
python -m pip install paddlepaddle-gpu==2.0.1.post90 -i https://mirror.baidu.com/pypi/simple

# CUDA10.1
python -m pip install paddlepaddle-gpu==2.0.1.post101 -f https://mirror.baidu.com/pypi/simple

# CPU
python -m pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple

# 在您的Python解释器中确认PaddlePaddle安装成功
>>> import paddle
>>> paddle.utils.run_check()

# 确认PaddlePaddle版本
python -c "import paddle; print(paddle.__version__)"

# pip安装paddledet
pip install paddledet==2.0.1 -i https://mirror.baidu.com/pypi/simple

# 下载使用源码中的配置文件和代码示例
git clone https://github.com/PaddlePaddle/PaddleDetection.git
cd PaddleDetection

# 克隆PaddleDetection仓库
cd <path/to/clone/PaddleDetection>
git clone https://github.com/PaddlePaddle/PaddleDetection.git

# 编译安装paddledet
cd PaddleDetection
python setup.py install

# 安装其他依赖
pip install -r requirements.txt

python ppdet/modeling/tests/test_architectures.py

.....
----------------------------------------------------------------------
Ran 5 tests in 4.280s
OK

# 在GPU上预测一张图片
export CUDA_VISIBLE_DEVICES=0
python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o use_gpu=true weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --infer_img=demo/000000014439.jpg