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.
模型分类输出的分类数错啦
版权声明：本文为weixin_45276304原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接和本声明。