当前位置：网站首页>报错：C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:699: block: [9,0,0],

报错：C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:699: block: [9,0,0],

2022-08-06 12:47:00 【像夏天一样热】

完整报错：

C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:699: block: [9,0,0], thread: [0,0,0] Assertion `srcIndex < srcSelectDimSize` failed.

输出embedding后的词向量后报错：

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.

原因：初始化的Embedding词表大小太小，数据没有找到对应词向量，可查看word2index字典大小与词表大小对比分析。

原网站

版权声明
本文为[像夏天一样热]所创，转载请带上原文链接，感谢
https://blog.csdn.net/qq_37356556/article/details/126036894

当前位置：网站首页>报错：C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:699: block: [9,0,0],

报错：C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\Indexing.cu:699: block: [9,0,0],

边栏推荐

猜你喜欢

随机推荐