SHL
是的，本模型梯度信息更多，训练时显存占用较大。推理时不存在这种情况。
@hlacikd @susanin1970 hi guys, thanks for all of your works on rk3588(rk3588s), actually it needs some adjustment while exporting onnx if you want to convert to rknn model, I've released...
btw, I didn't say any words about RK3588 in my paper, the edge device I use in my paper is Jetson AGX Xavier. > Hi guys, > > I have...
给的错误信息太少了，我也不知道。你先单卡试试能不能跑。
是的，在params/train/train_settings.yaml中第二个参数设置为 ```yaml weights: "./edgeyolo_coco.pth" ``` 便可使用这里提供的预训练权重开始训练，改为训练时的last.pth即可从断点继续训练 **建议使用训练开始时使用我们提供的预训练权重以保证更好的效果**
Actually I tried just now, the link is still available, maybe it's available only in China.
没改多少东西，都是为了方便按照我需要的方式导出onnx模型做的改动 主要就是ultralytics/yolo/engine/exporter.py中的Exporter类 还有一些其他地方的改动，不太记得了，都是因为运行时报错才改的，你自己慢慢试试，不报错就行。
generally it is because of the version of tensorrt(or pytorch? maybe), just see my terminal output and change your version the same as mine. btw, I've found a little bug...
your warning in your title does not matter, what matters is the error.
这是环境配置的问题，估计opencv的版本不对或者就是没装，或者没写进环境变量里。要么就是CMakelist.txt文件没按照自己的环境改。不过话说我这个项目也没给cpp文件啊，咋在这提ISSUE呢