PaddleX icon indicating copy to clipboard operation
PaddleX copied to clipboard

PaddlePaddle End-to-End Development Toolkit(『飞桨』深度学习全流程开发工具)

Results 466 PaddleX issues
Sort by recently updated
recently updated
newest added

Update the API_predict's returned infomation. the returned box‘s should be Lower left coordinate ## 文档修改 文档修改:测试发现predict预测方法返回的预测框的坐标为左下角坐标,文档中为左上角坐标

contributor

问题类型:模型部署 **问题描述** 部署环境:Jetson nano,Jetpack 4.5 python3.6+nv_jetson-cuda10.2-cudnn8-trt7 安装官方提供的库 paddlepaddle_gpu-2.1.0-cp36-cp36m-linux_aarch64.whl 代码步骤如:https://paddleinference.paddlepaddle.org.cn/demo_tutorial/cuda_jetson_demo.html config.EnableUseGpu(500, 0); [使用GPU报错,停用GPU正常。报错代码如下图 ![QQ图片20210701173757](https://user-images.githubusercontent.com/2766645/124102639-1f977780-da93-11eb-8c44-1e0b09d3c5f3.png)

问题类型:模型训练 **问题描述** PaddleX 1.3.11 版本,模型训练没有问题,但是在模型剪裁的时候报错了。报错内容如下: creating index... index created! Paddle Version: 1.8.5 PaddleX Version: 1.3.11 num_classes = 1 W0702 08:14:17.499222 211 device_context.cc:252] Please NOTE: device: 0, CUDA Capability: 86, Driver...

问题类型:模型部署 **问题描述** ======================== 利用官方提供的`yolov3_mobilenetv3_large_pruned`模型进行推理报错 ``` /usr/lib/python3/dist-packages/apport/report.py:13: DeprecationWarning: the imp module is deprecated in favour of importlib; see the module's documentation for alternative uses import fnmatch, glob, traceback, errno, sys, atexit,...

问题类型:模型部署 使用paddle训练faster-rcnn并导出__model__,__params__,model.yml三个文件,之后在model_infer.cpp中进行部署测试出现 fail to find arch in Paddledetection yaml file,No init can't predict 的问题

如题:在树莓派上跑YOLOV3模型报错,求大佬指点一下是什么原因? pi@raspberrypi:~/PaddleX/deploy/raspberry/build $ ./detector --model_dir=/models/yolov3_mobilenetv3.nb --image=/images/1.jpg --cfg_file=/cfg_file/model.yml [I 7/12 15:33: 0.978 ...wsy/Paddle-Lite/lite/core/device_info.cc:1074 Setup] 0 KB [I 7/12 15:33: 0.979 ...wsy/Paddle-Lite/lite/core/device_info.cc:1074 Setup] 0 KB [I 7/12 15:33: 0.979 ...wsy/Paddle-Lite/lite/core/device_info.cc:1074 Setup] 0...

问题类型:模型训练 AttributeError: module 'paddlex.cv.transforms' has no attribute 'Compose'

如题,即使用同样的模型,已经下载过一次,再次启动训练还是会去下载权重参数

This log file path is D:\PaddleX_workspace\projects\P0001\T0013\out.log 注意:标志为WARNING/INFO类的仅为警告或提示类信息,非错误信息 2021-07-13 17:46:46 [INFO] Starting to read file list from dataset... 2021-07-13 17:46:46 [INFO] 169 samples in file D:\PaddleX_workspace\datasets\D0001\train_list.txt creating index... index created! 2021-07-13...

问题类型:PaddleX可视化客户端 ![微信截图_20210714193236](https://user-images.githubusercontent.com/6490927/125615344-66338ea1-419a-4812-8b73-71367fa9b9a8.png) NVIDIA-SMI 441.22 Driver Version: 441.22 CUDA Version: 10.2 nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2019 NVIDIA Corporation Built on Wed_Oct_23_19:32:27_Pacific_Daylight_Time_2019 Cuda compilation tools, release 10.2, V10.2.89...