63/5000 I got an error CUDA error: device-side assert triggered when I trained my own dataset in BoxInst

[Midlesun]

def mul(a : float, b : Tensor) -> Tensor: return b * a ~~~~~ <--- HERE def add(a : float, b : Tensor) -> Tensor: return b + a RuntimeError: CUDA error: device-side assert triggered e /cuda/IndexKernel.cu:142: block: [0,0,0], thread: [33,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. C:/cb/pytorch_1000000000000/work/aten/src/ATen/native/cuda/IndexKernel.cu:142: block: [0,0,0], thread: [34,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. C:/cb/pytorch_1000000000000/work/aten/src/ATen/native/cuda/IndexKernel.cu:142: block: [0,0,0], thread: [35,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. C:/cb/pytorch_1000000000000/work/aten/src/ATen/native/cuda/IndexKernel.cu:142: block: [0,0,0], thread: [36,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. C:/cb/pytorch_1000000000000/work/aten/src/ATen/native/cuda/IndexKernel.cu:142: block: [0,0,0], thread: [37,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. C:/cb/pytorch_1000000000000/work/aten/src/ATen/native/cuda/IndexKernel.cu:142: block: [0,0,0], thread: [38,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. C:/cb/pytorch_1000000000000/work/aten/src/ATen/native/cuda/IndexKernel.cu:142: block: [0,0,0], thread: [39,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. C:/cb/pytorch_1000000000000/work/aten/src/ATen/native/cuda/IndexKernel.cu:142: block: [0,0,0], thread: [40,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. C:/cb/pytorch_1000000000000/work/aten/src/ATen/native/cuda/IndexKernel.cu:142: block: [0,0,0], thread: [41,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. C:/cb/pytorch_1000000000000/work/aten/src/ATen/native/cuda/IndexKernel.cu:142: block: [0,0,0], thread: [42,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. C:/cb/pytorch_1000000000000/work/aten/src/ATen/native/cuda/IndexKernel.cu:142: block: [0,0,0], thread: [43,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.

My data set only has 2 types of items. I modified _C.MODEL.FCOS.NUM_CLASSES=2 in defaults.py and registered my own data set in builtin and builtin_meta. This error occurred during training RuntimeError: CUDA error: device-side assert triggered /cuda/IndexKernel.cu:142: block: [0,0,0], thread: [33,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.

[Midlesun]

I would be very grateful if someone could help with the answer