# Video Classification with Omnivore

*Author: [Xinyu Ge](https://github.com/gexy185)*

<br />

## Description

A video classification operator generates labels (and corresponding scores) and extracts features for the input video.
It transforms the video into frames and loads pre-trained models by model names.
This operator has implemented pre-trained models from [Omnivore](https://arxiv.org/abs/2201.08377)
and maps vectors with labels provided by datasets used for pre-training.

<br />

## Code Example

Use the pretrained Omnivore model to classify and generate a vector for the given video path './archery.mp4' 
([download](https://dl.fbaipublicfiles.com/pytorchvideo/projects/archery.mp4)).

 *Write the pipeline in simplified style*:

- Predict labels (default):
```python
import towhee

(
    towhee.glob('./archery.mp4') 
          .video_decode.ffmpeg()
          .action_classification.omnivore(
            model_name='omnivore_swinT', topk=5)
          .show()
)
```
<img src="./result1.png" height="px"/>

*Write a same pipeline with explicit inputs/outputs name specifications*:

```python
import towhee

(
    towhee.glob['path']('./archery.mp4')
          .video_decode.ffmpeg['path', 'frames']()
          .action_classification.omnivore['frames', ('labels', 'scores', 'features')](
                model_name='omnivore_swinT')
          .select['path', 'labels', 'scores', 'features']()
          .show(formatter={'path': 'video_path'})
)
```

<img src="./result2.png" height="px"/>

<br />

## Factory Constructor

Create the operator via the following factory method

***video_classification.omnivore(
model_name='omnivore_swinT', skip_preprocess=False, classmap=None, topk=5)***

**Parameters:**

​	***model_name***: *str*

​	The name of pre-trained tsm model.

​    Supported model names:
- omnivore_swinT
- omnivore_swinS
- omnivore_swinB
- omnivore_swinB_in21k
- omnivore_swinL_in21k
- omnivore_swinB_epic

​	***skip_preprocess***: *bool*

​	Flag to control whether to skip video transforms, defaults to False.
If set to True, the step to transform videos will be skipped.
In this case, the user should guarantee that all the input video frames are already reprocessed properly,
and thus can be fed to model directly.

​	***classmap***: *Dict[str: int]*: 

​	Dictionary that maps class names to one hot vectors.
If not given, the operator will load the default class map dictionary.

​	***topk***: *int*

​	The topk labels & scores to present in result. The default value is 5.

## Interface

A video classification operator generates a list of class labels
and a corresponding vector in numpy.ndarray given a video input data.

**Parameters:**

​	***video***: *Union[str, numpy.ndarray]*

​	Input video data using local path in string or video frames in ndarray.


**Returns**: *(list, list, torch.Tensor)*

​	A tuple of (labels, scores, features),
which contains lists of predicted class names and corresponding scores.