movinet/README.md

# Video Classification with MoViNet

*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 [MoViNet](https://arxiv.org/abs/2103.11511)
and maps vectors with labels provided by datasets used for pre-training.

<br />

## Code Example

Use the pretrained Movinet model to classify and generate a vector for the given video path './jumpingjack.gif' 
([download](https://github.com/tensorflow/models/raw/f8af2291cced43fc9f1d9b41ddbf772ae7b0d7d2/official/projects/movinet/files/jumpingjack.gif)).

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

```python
from towhee import pipe, ops, DataCollection

p = (
    pipe.input('path')
        .map('path', 'frames', ops.video_decode.ffmpeg())
        .map('frames', ('labels', 'scores', 'features'),
             ops.action_classification.movinet(model_name='movineta0'))
        .output('path', 'labels', 'scores', 'features')
)

DataCollection(p('./jumpingjack.gif')).show()
```

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

<br />

## Factory Constructor

Create the operator via the following factory method

***video_classification.movinet(
model_name='movineta0', skip_preprocess=False, classmap=None, topk=5)***

**Parameters:**

​	***model_name***: *str*

​	The name of pre-trained MoViNet model.

​    Supported model names:
- movineta0
- movineta1
- movineta2
- movineta3
- movineta4
- movineta5

​	***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.



# More Resources

- [Computer Vision with FiftyOne | Milvus & Zilliz Cloud](https://zilliz.com/product/integrations/FiftyOne): nan
- [What is a Convolutional Neural Network? An Engineer's Guide](https://zilliz.com/glossary/convolutional-neural-network): Convolutional Neural Network is a type of deep neural network that processes images, speeches, and videos. Let's find out more about CNN.
- [Building a Video Analysis System with Milvus Vector Database - Zilliz blog](https://zilliz.com/blog/milvus-helps-analyze-videos-intelligently): Learn how Milvus powers the AI analysis of video content.
- [Multimodal RAG with Milvus and GPT-4o](https://zilliz.com/event/multimodal-rag-with-milvus-and-gpt-4o): Join us for a webinar for a demo of multimodal RAG with Milvus and GPT-4o
- [4 Steps to Building a Video Search System - Zilliz blog](https://zilliz.com/blog/building-video-search-system-with-milvus): Searching for videos by image with Milvus
- [What are Vision Transformers (ViT)? - Zilliz blog](https://zilliz.com/learn/understanding-vision-transformers-vit): Vision Transformers (ViTs) are neural network models that use transformers to perform computer vision tasks like object detection and image classification.
- [Everything You Need to Know About Zero Shot Learning - Zilliz blog](https://zilliz.com/learn/what-is-zero-shot-learning): A comprehensive guide to Zero-Shot Learning, covering its methodologies, its relations with similarity search, and popular Zero-Shot Classification Models.