zxq
zxq
same problem. cmd code: trtexec.exe --onnx=D:\code\python\mmocr\tools\deployment\tmp.onnx --saveEngine=D:\code\python\mmocr\tools\deployment\tmp.trt error info: [04/19/2022-17:31:31] [W] [TRT] onnx2trt_utils.cpp:220: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting...
> @Z-XQ Please note that the support of model deployment has been moved to [MMDeploy](https://github.com/open-mmlab/mmdeploy). Please have a try. Thank you for your relpy! MMDeploy is vary diffcult for me...
**envs:** windows **command:** cd MDS. python3 setup.py install **error:** 
在mainwindow.cpp有两处生成centralwidget=new CentralWInit2D(this); 分别是38行(2D模式下)和589行(3D模式下)。 其析构函数增加内如如下是不是好点: ``` MainWindow::~MainWindow() { // MainWindow new出来的centralwidget,就由MainWindow析构函数释放 if (centralwidget) { delete centralwidget; centralwidget = nullptr; } } ```
支持训练,且支持分布式训练