torch.select — PyTorch 2.7 documentation (original) (raw)

torch.select(input, dim, index) → Tensor¶

Slices the input tensor along the selected dimension at the given index. This function returns a view of the original tensor with the given dimension removed.

Note

If input is a sparse tensor and returning a view of the tensor is not possible, a RuntimeError exception is raised. In this is the case, consider usingtorch.select_copy() function.

Parameters

• input (Tensor) – the input tensor.
• dim (int) – the dimension to slice
• index (int) – the index to select with

Note

select() is equivalent to slicing. For example,tensor.select(0, index) is equivalent to tensor[index] andtensor.select(2, index) is equivalent to tensor[:,:,index].