Python部署#

确认开发环境已安装FastDeploy,参考FastDeploy安装安装预编译的FastDeploy,或根据自己需求进行编译安装。

本文档以PaddleDetection目标检测模型PPYOLOE为例展示CPU上的推理示例

1. 获取模型和测试图像#

import fastdeploy as fd

model_url = "https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz"
image_url - "https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg"
fd.download_and_decompress(model_url, path=".")
fd.download(image_url, path=".")

2. 加载模型#

model_file = "ppyoloe_crn_l_300e_coco/model.pdmodel"
params_file = "ppyoloe_crn_l_300e_coco/model.pdiparams"
infer_cfg_file = "ppyoloe_crn_l_300e_coco/infer_cfg.yml"
model = fd.vision.detection.PPYOLOE(model_file, params_file, infer_cfg_file)

3. 预测图片检测结果#

import cv2
im = cv2.imread("000000014439.jpg")

result = model.predict(im)
print(result)

4. 可视化图片预测结果#

vis_im = fd.vision.visualize.vis_detection(im, result, score_threshold=0.5)
cv2.imwrite("vis_image.jpg", vis_im)