-
### bug描述 Describe the Bug
paddleinference在cpu上推理rtdetr模型速度极慢，4000ms，怎么回事？
### 其他补充信息 Additional Supplementary Information
paddleinference在cpu上推理rtdetr模型速度极慢，4000ms，怎么回事？
-
### bug描述 Describe the Bug
镜像链接： registry.baidubce.com/device/paddle-dcu:dtk23.10.1-kylinv10-gcc73-py310
[验证文档链接：](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/hardware_support/dc…
-
I want to install Apollo9.0 in a server, and the GPU is RTX4090, the version of cuda driver is 535.161.07, the version of cuda is 12.2.
When compiling the source code following the [tutorial](https…
-
### Description
Today i've download your magnificent project. And I wrote sample from https://github.com/sdcb/PaddleSharp/blob/master/docs/ocr.md . It was worked perfectly, but very CPU demanding.
…
-
Hello,
First, thank you for your library and your great work!
I am using PaddleSharp in my project and I have activated the loggs with the boolean ```GLogEnabled``` It looks like it redirect the…
-
#### 问题描述 / Problem Description
打开TensorRT不使用动态Shape的情况下 只初始化一次OCR模型然后连续识别 识别速度越来越慢 一开始1S能识别5-6次 过几分钟之后越来越慢最后识别一张图片需要1S
#### 运行环境 / Runtime Environment
- OS:Windows11
- Paddle:PaddleInference
-…
-
It can run on Windows 10, but throw an exception on the windows server IIS. The error log is shown as below.
**ErrorLog**
```
2023-11-13 09:20:11,821 [ERROR] [(null)] [8] [IISHttpServer] [?] Conn…
-
Hi,
when trying to run the main.py, I am getting the following error:
```
Traceback (most recent call last):
File "main.py", line 157, in
test = FaceEval()
File "main.py", line 13,…
-
- [x] dygraph-to-static
- [x] PaddleInference
- [ ] Paddle2ONNX
- [ ] OnnxRuntime Infer
- [x] Paddle-Lite opt (x86、arm)
- [x] Paddle-Lite Infer (x86、arm)
-
问题类型：模型部署
**问题描述**
========================
1、paddlex的Manufacture SDK 目前只支持cuda10.2+cuda7.6+trt7.0的sdk，目前paddlex新版本GUI只支持cuda11系列，所以总体来讲有点不太方便，是否可以编译不同版本的sdk，cuda11.0 11.2这些，还有部分仅支持CPU的是否可以提供…