⚡️FastDeploy

⚡️FastDeploy是一款简单易用的推理部署工具箱。覆盖业界主流优质预训练模型并提供开箱即用的开发体验，包括图像分类、目标检测、图像分割、人脸检测、人体关键点识别、文字识别等多任务，满足开发者多场景，多硬件、多平台的快速部署需求。

发版历史

[v0.2.0] 2022.08.18 全面开源服务端部署代码，支持40+视觉模型在CPU/GPU，以及通过GPU TensorRT加速部署

支持模型

任务场景	模型	X64 CPU	Nvidia-GPU	Nvidia-GPU TensorRT
图像分类	PaddleClas/ResNet50	√	√	√
	PaddleClas/PPLCNet	√	√	√
	PaddleClas/EfficientNet	√	√	√
	PaddleClas/GhostNet	√	√	√
	PaddleClas/MobileNetV1	√	√	√
	PaddleClas/MobileNetV2	√	√	√
	PaddleClas/ShuffleNetV2	√	√	√
目标检测	PaddleDetection/PPYOLOE	√	√	√
	PaddleDetection/PicoDet	√	√	√
	PaddleDetection/YOLOX	√	√	√
	PaddleDetection/YOLOv3	√	√	√
	PaddleDetection/PPYOLO	√	√	-
	PaddleDetection/PPYOLOv2	√	√	-
	PaddleDetection/FasterRCNN	√	√	-

快速开始

安装FastDeploy Python

用户根据开发环境选择安装版本，更多安装环境参考安装文档.

pip install https://bj.bcebos.com/paddlehub/fastdeploy/wheels/fastdeploy_python-0.2.0-cp38-cp38-manylinux1_x86_64.whl

准备目标检测模型和测试图片

wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz
tar xvf ppyoloe_crn_l_300e_coco.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg

加载模型预测

import fastdeploy.vision as vis
import cv2

model = vis.detection.PPYOLOE("ppyoloe_crn_l_300e_coco/model.pdmodel",
                              "ppyoloe_crn_l_300e_coco/model.pdiparams",
                              "ppyoloe_crn_l_300e_coco/infer_cfg.yml")

im = cv2.imread("000000014439.jpg")
result = model.predict(im.copy())
print(result)

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

预测完成，可视化结果保存至vis_image.jpg，同时输出检测结果如下

DetectionResult: [xmin, ymin, xmax, ymax, score, label_id]
415.047363,89.311523, 506.009613, 283.863129, 0.950423, 0
163.665710,81.914894, 198.585342, 166.760880, 0.896433, 0
581.788635,113.027596, 612.623474, 198.521713, 0.842597, 0
267.217224,89.777321, 298.796051, 169.361496, 0.837951, 0
104.465599,45.482410, 127.688835, 93.533875, 0.773348, 0
...

License

FastDeploy遵循Apache-2.0开源协议。

6.0 KiB Raw Blame History Unescape Escape