xiaoyaoguai

>  > > It's predicting the class id that I haven't trained, and it's predicting a lot of random bounding grays. I didn't know...

try this：rebuild the "yolo_layer.h" in plugin, line70: bool supportsFormatCombination(int pos, const PluginTensorDesc* inOut, int nbInputs, int nbOutputs) const NOEXCEPT override { return inOut[pos].format == PluginFormat::kLINEAR && inOut[pos].type == DataType::kFLOAT; }