torch.unsqueeze

Returns a new tensor with a dimension of size one inserted at the specified position.

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.Tensor.scatter_add_

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

torch.squeeze

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

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.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.matmul

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

torch.transpose

Returns a tensor that is a transposed version of input . The given dimensions dim0 and dim1 ...

torch.add

Supports broadcasting to a common shape, type promotion, and integer, float, and complex inputs. Parameters: input (Tensor) – the input 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 ...