Returns a new tensor with a dimension of size one inserted at the specified position.
by its index in src for dimension != dim and by the corresponding value in ...
Returns a tensor with all the dimensions of input of size 1 removed. For example, if input is of shape: ...
Pads tensor. Padding size: The padding size by which to pad some dimensions of input are described starting from the last dimension and ...
Returns the sum of each row of the input tensor in the given dimension dim . If dim is a list of dimensions, reduce over all of them.
Returns a new view of the self tensor with singleton dimensions expanded to a larger size. Passing -1 as the size for a dimension means not changing the size of ...
other (Tensor or Number) – the tensor or number to add to input. Keyword Arguments: alpha (Number) – the multiplier for other . out ...
For a tensor to be viewed, the new view size must be compatible with its original size and stride, i.e., each new view dimension must either be a subspace ...
torch.Tensor.repeat. Tensor.repeat(*sizes) → Tensor. Repeats this tensor along the specified dimensions. Unlike expand() , this function copies the ...
On certain ROCm devices, when using float16 inputs this module will use ...