failed to initialize database, got error Binary was compiled with 'CGO_ENABLED=0', go-sqlite3 requires cgo to work. This is a stub panic: failed to connect database

这个错误可能是因为你的go-sqlite3库需要cgo来工作，而cgo在编译程序时被禁用了。你可以尝试启用CGO以解决这个问题。

在编译程序时，确保使用CGO_ENABLED=1的标志启用cgo。例如：

CGO_ENABLED=1 go build

如果你使用的是go mod，请在go.mod文件中添加以下行：

replace github.com/mattn/go-sqlite3 => github.com/mattn/go-sqlite3 cgo

然后再次运行go mod tidy。

希望这能帮助你解决问题！

相关问题

(0) unknown: failed to get convolution algorithm. this is probably because cudnn failed to initialize, so try looking to see if a warning log message was printed above.

Q: "b'(0) unknown: failed to get convolution algorithm. this is probably because cudnn failed to initialize, so try looking to see if a warning log message was printed above.'." 的意思是什么？

A: 这个错误提示表示在获取卷积算法时出现了问题，原因很可能是因为CUDNN未能正确初始化。建议查看上面是否有警告日志消息。

D:\python3.10\lib\site-packages\torch\nn\modules\linear.py:96: UserWarning: Failed to initialize NumPy: module compiled against API version 0x10 but this version of numpy is 0xf . Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem . (Triggered internally at ..\torch\csrc\utils\tensor_numpy.cpp:84.) self.weight = Parameter(torch.empty((out_features, in_features), **factory_kwargs)) Traceback (most recent call last): File "C:\Users\admin\PycharmProjects\dl1test\main.py", line 46, in <module> data_train = torch.tensor(x_train).float() RuntimeError: Could not infer dtype of numpy.uint8

这个警告提示是因为 NumPy 的版本和 Torch 包中的线性层模块不兼容，需要通过查看在 https://numpy.org/devdocs/user/troubleshooting-importerror.html 中关于 C-API 不兼容的部分来解决 ImportError 的问题。