RuntimeError: view size is not compatible with input tensor‘s size and stride

在运行pytorch程序中：

def forward(self, x):out = self.cnn(x)out = out.view(out.size()[0], -1)return self.fc(out)

python报错：

RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

这是因为view()需要Tensor中的元素地址是连续的，但可能出现Tensor不连续的情况，所以先用 .contiguous() 将其在内存中变成连续分布：

out = out.contiguous().view(out.size()[0], -1)

这样就好了。

RuntimeError: view size is not compatible with input tensor‘s size and stride相关推荐

报错：RuntimeError: view size is not compatible with input tensor‘s size and stride (at least one dimen
报错:RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimen ...
深度学习：view size is not compatible with input tensor‘s size and stride (at least one dimension spans a
错误提示: view size is not compatible with input tensor's size and stride (at least one dimension spans ...
运行错误：view size is not compatible with input tensor‘s size and stride (at least
python运行报错: view size is not compatible with input tensor's size and stride (at least one dimension ...
Python总结:RuntimeError: matplotlib does not support generators as input
QUESTION:RuntimeError: matplotlib does not support generators as input? ANSWER: 例子: 来源:stackoverflow ...
RuntimeError: non-empty 3D or 4D input tensor expected but got ndim: 4
在使用pytorch训练模型时报,以下错误: RuntimeError: non-empty 3D or 4D input tensor expected but got ndim: 4 当把一个空的 ...
cannot assign slice from input of different size
这个问题的提示挺明显的,就是维数不匹配,问题是怎么找到这个出问题的地方. 首先因为我使用的是numba 加速,编译之后运行的提示给的是cannot assign slice from input of ...
pytorch(2)Tensor创建和获取tensor的size信息、torch.dtype、torch.device、torch.layout
获取tensor的size信息 >>> import torch >>> from torch.autograd import Variable >>& ...
python size和count_groupby 的妙用（注意size和count）
Pandas的groupby()功能很强大,用好了可以方便的解决很多问题,在数据处理以及日常工作中经常能施展拳脚. 今天,我们一起来领略下groupby()的魅力吧. 首先,引入相关package: ...
entrypoint size limit: The following entrypoint(s) combined asset size exceeds the recommended limit
webpack打包提示文件体积过大导致 The following asset(s) exceed the recommended size limit (244 KiB). This can imp ...

RuntimeError: view size is not compatible with input tensor‘s size and stride

RuntimeError: view size is not compatible with input tensor‘s size and stride相关推荐

最新文章

热门文章