0
# Video Metrics
1

2
Specialized metrics for video quality assessment and evaluation, focusing on perceptual quality measures for video processing applications.
3

4
## Capabilities
5

6
### Video Quality Assessment
7

8
Advanced metrics for evaluating video quality (require optional dependencies).
9

10
```python { .api }
11
class VideoMultiMethodAssessmentFusion(Metric):
12
    def __init__(
13
        self,
14
        **kwargs
15
    ): ...
16
```
17

18
## Usage Examples
19

20
```python
21
import torch
22
from torchmetrics.video import VideoMultiMethodAssessmentFusion
23

24
# Video quality assessment with VMAF
25
try:
26
    vmaf = VideoMultiMethodAssessmentFusion()
27
    
28
    # Sample video tensors (batch, channels, time, height, width)
29
    preds = torch.randint(0, 256, (1, 3, 30, 480, 640), dtype=torch.uint8)  # 30 frames
30
    target = torch.randint(0, 256, (1, 3, 30, 480, 640), dtype=torch.uint8)
31
    
32
    # Compute VMAF score
33
    vmaf_score = vmaf(preds, target)
34
    print(f"VMAF Score: {vmaf_score:.4f}")
35
    
36
except ImportError:
37
    print("VMAF requires the 'torch-vmaf' package")
38
```
39

40
## Types
41

42
```python { .api }
43
VideoTensor = Tensor  # Shape: (batch, channels, time, height, width)
44
```