PaddlePaddle/FastDeploy
⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models with end-to-end optimization, multi-platform and multi-framework support.
C++Apache-2.0
Issues
- 0
# 预测结果可视化 vis_im = fd.vision.vis_detection(im, result, score_threshold=0.5) windows 下写出的文件为空白
#2577 opened by xujiang1 - 1
- 2
这个仓库后续还继续更新吗?另外如果更新的话,可以考虑目前的大语言模型、视觉大模型的部署那就更好了
#2566 opened by GLaStu - 11
yolov11 能增加不
#2529 opened by monkeycc - 0
OCR的REC模型,能用RCNN的吗,比如rec_r50_fpn_srn
#2575 opened by monkeycc - 0
PP-OCRv4 在没检测到文本的时候,结果出错
#2574 opened by ChaoII - 2
PP-OCRv4,什么时候增加
#2571 opened by monkeycc - 0
FastDeploy在昇腾部署PaddleOCR(文字检测+文字识别)发现存在耗时的问题
#2573 opened by zznnxx - 2
加载PPYOLOE+模型时报错
#2537 opened by CashBai - 1
C++SDK如何关闭日志啊
#2572 opened by monster-arch - 5
使用官方文字cls模型转onnx正常再转rknn报错
#2567 opened by Zomcxj - 4
请问下使用fastdeploy部署paddleOCRv3的性能问题
#2570 opened by ouerum - 1
无法正常运行ppocrv4_rec_server,其他可以正常运行
#2558 opened by sunzx8 - 0
FastDeploy对AMD GPU / 海光DCU的支持问题
#2568 opened by cerasumat - 0
咨询:fd是否支持pp-yoloe-r旋转框检测?
#2565 opened by njflove - 2
Python统计耗时明显高于模型内置统计耗时
#2536 opened by ucsk - 0
开启paddlelite支持在aarch64架构上编译不成功
#2556 opened by Strepsiades - 1
关于C# FastDeploy部署,编译后找不到C# 动态库文件 fastdeploy_csharp.dll
#2555 opened by caojun226 - 0
FastDeploy c++部署ppyoloe_r 旋转框预测异常
#2552 opened by ifluck - 1
华为昇腾310p编译安装出现CANN版本不匹配的问题
#2550 opened by Hakstar - 3
yolov 8推理输出的目标检测框大小不正确
#2549 opened by huangguifeng - 1
TrtBackend::LoadTrtCache加载tensorrt模型时报错
#2547 opened by aidenyao - 2
- 0
TrtBackend::LoadTrtCache加载tensorrt模型时报错
#2544 opened by aidenyao - 1
OCSort里的iou_batch与Python版本算法不一致
#2545 opened by terrencew - 3
自训练了ocr的det模型,用的v3,但是在Android中运行报错,直接用demo能够正常运行,求解答
#2538 opened by mozeqiu123 - 0
华为Ascend310P卡死了
#2543 opened by jo-dean - 0
cannot open shared object file: No such file or directory
#2540 opened by jo-dean - 0
在安卓端实现目标跟踪
#2539 opened by Edward-YS - 1
自行编译的fastdeploy无法使用gpu进行推理
#2533 opened by tammy-na - 1
关于算法后处理设计疑问,以yolov5为例
#2534 opened by mailliw2010 - 0
调用uie的c++代码,循环调用predict函数,出现内存一直增长
#2535 opened by lhx150926 - 0
请问一下fastdeploy_serving支持ascend(310/910)系列部署吗?
#2532 opened by cgq0816 - 2
相同的模型结构,不同的参数,预测时间差异很大
#2531 opened by terrencew - 1
部署llm是否使用paddlepaddle2.6也可以?和使用nightly的区别是什么?
#2527 opened by Aganlengzi - 1
镜像Dockerfile问题请教
#2528 opened by Aganlengzi - 1
linux_aarch64的安装包1.0.2之后没有了,希望能够支持后续版本
#2530 opened by walaiwalai - 4
OCR Cpu与Gpu推理结果不一致,Cpu错误
#2519 opened by panshuaisharon - 1
Csharp 推理异常闪退
#2518 opened by hjm950118 - 1
华为昇腾支持cann7.0吗?
#2517 opened by intjun - 0
希望能够支持华为910b3,cann8.0
#2521 opened by bltcn - 0
Fastdeploy服务化部署时failed to load model 'cls_runtime': at least one version must be available under the version policy of model 'cls_runtime'
#2512 opened by IceHowe - 2
测试rvm Pfld Pipnet 感觉都有点问题
#2510 opened by chfeizy - 4
重复刷新模型造成的内存泄露问题
#2511 opened by Algabeno - 8
- 0
模型直接推理没错,服务化部署后,客户端请求后结果不对
#2514 opened by IceHowe - 0
Fastdeploy服务化部署模型后,客户端请求失败
#2513 opened by IceHowe - 0
cpu部署库移植报错
#2508 opened by Zomcxj - 1
使用FD部署Paddleseg生成的模型时报错
#2507 opened by CashBai - 2
使用Fastdeploy之后就无法导入Taskflow?另外同一进程无法加载两个Fastdeploy模型?
#2506 opened by Strepsiades