loss.backward()处遇到“RuntimeError: Found dtype Double but expected Float”

企业开发 2023-07-29 02:42:46 阅读次数: 0

错误信息

类型错误, 计算loss值的函数传入的参数类型不统一。

解决方法

查看上文loss计算代码部分的参数类型，如loss=f.mse_loss(out,label)，检查out和label的类型都是torch.float类型即可。使用label.dtype查看tensor的类型。

具体流程

报错定位在这一行

在这里插入图片描述
寻思着是否是loss类型的问题，于是我就添加

loss = loss.to(torch.float32)

但是还是报错在此处，于是开始考虑是否是上文loss计算代码部分的参数类型有问题
在这里插入图片描述
添加这两行，再次运行，sucess，完美

猜你喜欢

转载自blog.csdn.net/qq_44391957/article/details/127109170

loss.backward()处遇到“RuntimeError: Found dtype Double but expected Float”

loss.backward()引发“RuntimeError: Found dtype Double but expected Float”

torch 写模型遇到 RuntimeError: Found dtype Double but expected Float

RuntimeError_ Found dtype Long but expected Float

报错：RuntimeError: expected scalar type Double but found Float

成功解决 RuntimeError:expected scalar type Double but found Float

PyTorch:expected scalar type Float but found Double

图神经网络 RuntimeError: expected scalar type Double but found Float

错误ValueError: Buffer dtype mismatch, expected ‘float32_t‘ but got ‘double

tf.matmul()报错expected scalar type Float but found Double

RuntimeError: expected scalar type Long but found Float

RuntimeError: expected scalar type Half but found Float

RuntimeError: expected scalar type float but found __int64

RuntimeError: Expected object of scalar type Double but got scalar type Float for argument #2 'mat2'

RuntimeError: Expected object of scalar type Float but got scalar type Double for argument #2 ‘mat1‘

expected scalar type float but found half

LLM-大模型训练-常见错误：RuntimeError: expected scalar type Half but found Float

RuntimeError: expected device cuda:0 and dtype Byte but got device cuda:0 and dtype Bool

RuntimeError: scatter_cpu_(): Expected self.dtype to be equal to src.dtype

float与double

double与float

cannot compute MatMul as input #1(zero-based) was expected to be a double tensor but is a float...

RuntimeError: Could not infer dtype of numpy.float32 问题解决

float 和 double 的精度

java float vs double

Char、float、Double、BigDecimal

float,double判断相等

float和double的区别

double 与 float的比较

float，double精度

今日推荐

周排行

成为C++高手之宏与枚举

在CAD二次开发中使用进度条

Js插件ECharts，HighCharts学习网址整理

Celery提交任务出错(on windows.)

cephfs内核客户端性能追踪

thinkphp中PHPExcel用法

EntityFramework动态组合多排序字段

汇编语言（八）实验9 根据材料编程

安装ubuntu后必须做的事情（对我而言）

JS函数式编程

每日归档

2024-10-22(0)

2024-10-21(0)

2024-10-20(0)

2024-10-19(0)

2024-10-18(0)

2024-10-17(0)

2024-10-16(0)

2024-10-15(0)

2024-10-14(0)

2024-10-13(0)