【PyTorch】Pytorch踩坑记
pytorch踩坑记
错误1:UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
copy# bug :
feature = torch.tensor(torch.from_numpy(feature), dtype=torch.float32)
# debug :
# 改为:
feature = torch.as_tensor(torch.from_numpy(feature), dtype=torch.float32)
错误2:RuntimeError: Expected object of scalar type Float but got scalar type Double for argument #2 ‘mat1’ in call to _th_addmm
copy# debug :
feature = torch.as_tensor(torch.from_numpy(feature), dtype=torch.float32)
错误3:UserWarning: Using a target size (torch.Size([64])) that is different to the input size (torch.Size([64,1]))
copy# debug :
# 在forward(self, x)函数体中,在return x之前,加一句
x = x.squeeze(-1)
【推荐】国内首个AI IDE,深度理解中文开发场景,立即下载体验Trae
【推荐】编程新体验,更懂你的AI,立即体验豆包MarsCode编程助手
【推荐】抖音旗下AI助手豆包,你的智能百科全书,全免费不限次数
【推荐】轻量又高性能的 SSH 工具 IShell:AI 加持,快人一步