# Image Embedding with data2vec

*author: David Wang*


<br />



## Description

This operator extracts features for image with [data2vec](https://arxiv.org/abs/2202.03555). The core idea is to predict latent representations of the full input data based on a masked view of the input in a self-distillation setup using a standard Transformer architecture.

<br />


## Code Example

Load an image from path './towhee.jpg' to generate an image embedding. 

 *Write the pipeline in simplified style*:

```python
import towhee

towhee.glob('./towhee.jpg') \
      .image_decode.cv2() \
      .image_embedding.data2vec(model_name='facebook/data2vec-vision-base-ft1k') \
      .show()

```
<img src="./result1.png" alt="result1" style="height:20px;"/>

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

```python
import towhee

towhee.glob['path']('./towhee.jpg') \
      .image_decode.cv2['path', 'img']() \
      .image_embedding.data2vec['img', 'vec'](model_name='facebook/data2vec-vision-base-ft1k') \
      .select['img', 'vec']() \
      .show()
```
<img src="./result2.png" alt="result2" style="height:60px;"/>


<br />



## Factory Constructor

Create the operator via the following factory method

***data2vec(model_name='facebook/data2vec-vision-base')***

**Parameters:**


​  ***model_name***: *str*

The model name in string.
The default value is "facebook/data2vec-vision-base-ft1k".

Supported model name:
- facebook/data2vec-vision-base-ft1k
- facebook/data2vec-vision-large-ft1k

<br />



## Interface

An image embedding operator takes a [towhee image](link/to/towhee/image/api/doc) as input.
It uses the pre-trained model specified by model name to generate an image embedding in ndarray.


**Parameters:**

​	***img:*** *towhee.types.Image (a sub-class of numpy.ndarray)* 

​	The decoded image data in towhee.types.Image (numpy.ndarray).



**Returns:** *numpy.ndarray*

​   The image embedding extracted by model.