This post explains how to calculate `Cosine Similarity`

in `PyTorch`

.
`torch.nn.functional`

module provides `cosine_similarity`

method for calculating `Cosine Similarity`

```
import torch
import torch.nn.functional as F
```

```
tensor1 = torch.randn(50)
tensor2 = torch.randn(50)
```

`Cosine Similarity`

```
cosine_similarity_value = F.cosine_similarity(tensor1, tensor2, dim=0)
print(cosine_similarity_value)
#### Output ####
tensor(-0.2427)
```

Categories: PyTorch