search

SHI-Labs / Neighborhood-Attention-Transformer

Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022
MIT License
1.04k stars 85 forks source link

Assertion `idx_dim >= 0 && idx_dim < index_size && "index out of bounds"` failed. #41

Closed YangParky closed 2 years ago

YangParky commented 2 years ago

Hi, thanks for your excellent work, I found this problem when I apply it on other tasks. sys enviroment: 3090Ti，torch：1.10，CUDA-11.3 EPOCH 1 learning rate = [0.0001] /opt/conda/conda-bld/pytorch_1634272168290/work/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:111: operator(): block: [45,0,0], thread: [21,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed. /opt/conda/conda-bld/pytorch_1634272168290/work/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:111: operator(): block: [45,0,0], thread: [22,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed. /opt/conda/conda-bld/pytorch_1634272168290/work/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:111: operator(): block: [45,0,0], thread: [23,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed. /opt/conda/conda-bld/pytorch_1634272168290/work/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:111: operator(): block: [45,0,0], thread: [24,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed. /opt/conda/conda-bld/pytorch_1634272168290/work/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:111: operator(): block: [45,0,0], thread: [25,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.