PyTorch torch.adjoint() method **“returns a view of the tensor conjugated and with the last two dimensions transposed.”**

**Syntax**

`torch.adjoint(`*Tensor*)

**Parameters**

**Tensor:** It is an input tensor.

**Example 1: Basic usage with a 2D complex tensor**

```
import torch
tensor_1 = torch.tensor([[1 + 1j, 2 + 2j], [3 + 3j, 4 + 4j]])
adjoint_1 = torch.adjoint(tensor_1)
print("Original Tensor:")
print(tensor_1)
print("\nAdjoint Tensor:")
print(adjoint_1)
```

**Output**

**Example 2: Using the method with higher-dimensional tensors**

```
import torch
tensor_2 = torch.tensor([
[[1 + 1j, 2 + 2j], [3 + 3j, 4 + 4j]],
[[5 + 5j, 6 + 6j], [7 + 7j, 8 + 8j]]
])
adjoint_2 = torch.adjoint(tensor_2)
print("Original Tensor:")
print(tensor_2)
print("\nAdjoint Tensor:")
print(adjoint_2)
```

**Output**

**Example 3: Using the method with real numbers**

```
import torch
tensor_3 = torch.tensor([[1, 2], [3, 4]])
adjoint_3 = torch.adjoint(tensor_3)
print("Original Tensor:")
print(tensor_3)
print("\nAdjoint Tensor:")
print(adjoint_3)
```

**Output**

For real numbers, the adjoint is the same as the regular transpose since there’s no complex component to conjugate.

**Related posts**

Krunal Lathiya is a seasoned Computer Science expert with over eight years in the tech industry. He boasts deep knowledge in Data Science and Machine Learning. Versed in Python, JavaScript, PHP, R, and Golang. Skilled in frameworks like Angular and React and platforms such as Node.js. His expertise spans both front-end and back-end development. His proficiency in the Machine Learning frameworks like PyTorch and Tensorflow is a testament to his versatility and commitment to the craft.