CuDNN error: CUDNN_STATUS_INTERNAL_ERROR

[J-zin]

hi, i use it to train for my own data set, but it run error, can u give me some suggestion? (my segmentation class img is gray image).

/opt/conda/conda-bld/pytorch_1532581333611/work/aten/src/THCUNN/SpatialClassNLLCriterion.cu:99: void cunn_SpatialClassNLLCriterion_updateOutput_kernel(T *, T *, T *, long *, T *, int, int, int, int, int, long) [with T = float, AccumT = float]: block: [3,0,0], thread: [190,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1532581333611/work/aten/src/THCUNN/SpatialClassNLLCriterion.cu:99: void cunn_SpatialClassNLLCriterion_updateOutput_kernel(T *, T *, T *, long *, T *, int, int, int, int, int, long) [with T = float, AccumT = float]: block: [3,0,0], thread: [191,0,0] Assertion t >= 0 && t < n_classes failed. Traceback (most recent call last): File "train.py", line 234, in main() File "train.py", line 215, in main loss.backward() File "/home/zhangjunyi/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/tensor.py", line 93, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "/home/zhangjunyi/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/autograd/init.py", line 90, in backward allow_unreachable=True) # allow_unreachable flag RuntimeError: CuDNN error: CUDNN_STATUS_INTERNAL_ERROR

[J-zin]

i got it, the gray num must be lower than the class nums!!!

[Raven1327]

i got it, the gray num must be lower than the class nums!!!

I got the same problem. Could you please teach me how to fix it?

[speedinghzl]

@Raven1327 Do you run this repo on PASCAL VOC dataset or another dataset? You can simply modify the NUM_CLASSES in this line for your dataset.

[Raven1327]

@speedinghzl Thanks for your help. It can run now. I made some mistakes. T-T

[Lixy1997]

@speedinghzl I use VOC dataset， NUM_CLASSED=21, i also get the same problem