YouTip

# PyTorch torch.add Function * * Pytorch torch reference manual](#) `torch.add` is a function in PyTorch used to perform element-wise addition. It adds two tensors or a tensor and a scalar. This is one of the most basic mathematical operations, which will be used in various computational scenarios in deep learning. ### Function Definition torch.add(input, other, alpha=1, out=None) **Parameters**: * `input` (Tensor): The first input tensor. * `other` (Tensor or float): The second input tensor or scalar. * `alpha` (float, optional): Scaling factor; `other` will be multiplied by this value before being added to `input`, default is 1. * `out` (Tensor, optional): Output tensor. **Return Value**: * `torch.Tensor`: Returns the tensor after addition. * * * ## Usage Examples ### Example 1: Adding Two Tensors ## Instance import torch # Create two tensors a = torch.tensor([1,2,3]) b = torch.tensor([4,5,6]) # Add them together c = torch.add(a, b) print(c) Output result: tensor([5, 7, 9]) ### Example 2: Tensor Plus Scalar ## Instance import torch # Create a tensor a = torch.tensor([1,2,3]) # Add scalar b = torch.add(a,10) print(b) Output result: tensor([11, 12, 13]) ### Example 3: Using the alpha Parameter ## Instance import torch # Create two tensors a = torch.tensor([1.0,2.0,3.0]) b = torch.tensor([1.0,2.0,3.0]) # Calculate a + 2 * b c = torch.add(a, b, alpha=2) print(c) Output result: tensor([3., 6., 9.]) The `alpha` parameter is useful when implementing certain algorithms, such as computing `input + alpha * other`. ### Example 4: Broadcasting Mechanism ## Instance import torch # Add tensors of different shapes (broadcasting) a = torch.tensor([[1,2,3],[4,5,6]]) b = torch.tensor([1,2,3]) c = torch.add(a, b) print(c) Output result: tensor([[2, 4, 6], [5, 7, 9]]) PyTorch supports broadcasting mechanism, allowing operations on tensors of different shapes. * * * ## Using the Plus Operator Besides using the `torch.add()` function, you can also directly use the `+` operator, both have the same effect: ## Instance import torch a = torch.tensor([1,2,3]) b = torch.tensor([4,5,6]) # Both methods are equivalent c1 = torch.add(a, b) c2 = a + b print(c1) print(c2) print(torch.equal(c1, c2)) * * Pytorch torch reference manual](#)