橙子啊橙子

PPLCNet onnx2ncnn

1

when i try to convert PPLCNet from onnx to ncnn, ncnn error report "Shape not support yet! Unknown data type 0"

error about cpp code

1

[ INFO:0] global C:\jenkins\workspace\OpenCV\OpenVINO\2021.2\build\windows\opencv\modules\dnn\src\onnx\onnx_importer.cpp (395) cv::dnn::dnn4_v20201117::ONNXImporter::populateNet DNN/ONNX: loading ONNX v6 model produced by 'pytorch':1.7. Number of nodes = 335, inputs = 1, outputs = 6

deepsort提取特征维度问题

4

大佬，我把deepsort转换为openvino模型，但是deepsort输出为512*1维的向量，所以我想问一下为啥你的FeatureDim设置为256啊

Fastdeploy在JetsonNano上，通过TensorRT调用picodet，内存占用过高问题。

1

## 环境 - 【编译命令】cmake .. -DBUILD_ON_JETSON=ON \ -DENABLE_VISION=ON \ -DENABLE_PADDLE_BACKEND=OFF\ -DPADDLEINFERENCE_DIRECTORY=/Download/paddle_inference_jetson \ -DCMAKE_INSTALL_PREFIX=${PWD}/installed_fastdeploy - 【系统平台】: Linux x64(Ubuntu 18.04) - 【硬件】： JetsonNano， CUDA 10.2.300 CUDNN 8.2.1.32 - 【编译语言】： C++ ## 问题日志及出现问题的操作流程...