torch.cumsum#

torch.cumsum(input,dim,*,dtype=None,out=None)→Tensor#

Returns the cumulative sum of elements ofinput in the dimensiondim.

For example, ifinput is a vector of size N, the result will also bea vector of size N, with elements.

$$y_i=x_1+x_2+x_3+\cdots +x_i$$yi​=x1​+x2​+x3​+⋯+xi​

Parameters

• input (Tensor) – the input tensor.

• dim (int) – the dimension to do the operation over

Keyword Arguments

• dtype (torch.dtype, optional) – the desired data type of returned tensor.If specified, the input tensor is casted todtype before the operationis performed. This is useful for preventing data type overflows. Default: None.

• out (Tensor,optional) – the output tensor.

Example:

>>>a=torch.randint(1,20,(10,))>>>atensor([13,  7,  3, 10, 13,  3, 15, 10,  9, 10])>>>torch.cumsum(a,dim=0)tensor([13, 20, 23, 33, 46, 49, 64, 74, 83, 93])