【无标题】For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

RuntimeError: CUDA error: device-side assert triggered
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

问题：一般是类别不一致导致的，网络输出类别跟输入数据类别不一致导致，我的数据集是15各类别，网络输出类别设置的14不一致导致的。

解决方法：确认数据集种类别数，修改网络输出类别数

我的代码修改部分如下所示，将num_classes修改为15：

model.head.postprocessor.iou_thr = 0.6
model.head.postprocessor.score_thr = 0.001
model.head.postprocessor.multi_label = True
model.head.headmodule.num_classes = 15