torch.unsqueeze

dim (int) – the index at which to insert the singleton dimension.

torch.Tensor.expand

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 ...

torch.squeeze

Returns a tensor with all the dimensions of input of size 1 removed. For example, if input is of shape: ...

torch.sum

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.

torch.Tensor.repeat

torch.Tensor.repeat. Tensor.repeat(*sizes) → Tensor. Repeats this tensor along the specified dimensions. Unlike expand() , this function copies the ...

torch.stack

dim (int) – dimension to insert. Has to be between 0 and the number of dimensions of concatenated tensors (inclusive). Keyword Arguments: out (Tensor, ...

torch.Tensor.view

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.nn.functional.pad

Pads tensor. Padding size: The padding size by which to pad some dimensions of input are described starting from the last dimension and ...

torch.Tensor.scatter_add_

by its index in src for dimension != dim and by the corresponding value in ...

torch.matmul

On certain ROCm devices, when using float16 inputs this module will use different ...