Yi-hash1

部署yolov7后，推理的时候有警告，求大佬看看

2

[2023-09-21 04:18:00][warn][trt_builder.cpp:33]:NVInfer: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.

Yolov8部署jetson后map精度问题

2

我将训练好的yolov8模型部署到jetson nano中，并利用tensorrt加速，我发现相对于在服务器中推理验证集map50指标下降了5%，请问是由于jetson nano的算力问题导致精度下降，还是有别的原因

onnx转换trt报错

1

[04/10/2024-16:11:31] [W] [TRT] onnx2trt_utils.cpp:366: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32. [04/10/2024-16:11:32] [I] Finish parsing...

yolov8原网络改进

1

yolov8原网络改进后，还可以直接使用您这个方法进行部署吗，还是需要做哪些修改吗

需要更改这个仓库什么文件，才能让我部署到我的jetson上

使用trtexec工具将onnx转换trt问题

1

有警告Some tactics do not have sufficient workspace memory to run. Increasing workspace size may increase performance, please check verbose output.，该警告会影响模型的推理速度或精度吗

部署改进的v8模型的时候，make yolo报错

1

 Segmentation fault (core dumped) Makefile:99: recipe for target 'yolo' failed make: *** [yolo] Error 139 设备：jetson nano 4GB 是因为算力不够吗，还是别的原因，求解答

make yolo报错

2

 NVInfer: 3: [executionContext.cpp::setBindingDimensions::944] Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::setBindingDimensions::944, condition: profileMaxDims.d[i] >= dimensions.d[i]. Supplied binding dimension [2,3,640,640] for bindings[0] exceed min ~ max range...