# Image Embdding with DOLG

*author: David Wang*



## Desription

This operator extracts features for image with [DOLG](https://arxiv.org/abs/2108.02927) which has special design for image retrieval task. It integrates local and global information inside images into compact image representations. This operator is an adaptation from [dongkyuk/DOLG-pytorch](https://github.com/dongkyuk/DOLG-pytorch).

## 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.dolg(img_size=512, input_dim=3, hidden_dim=1024, output_dim=2048) \
      .show()

```
<img src="https://towhee.io/image-embedding/dolg/raw/branch/main/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.dolg['img', 'vec'](img_size=512, input_dim=3, hidden_dim=1024, output_dim=2048) \
      .select('img', 'vec') \
      .show()
```
<img src="https://towhee.io/image-embedding/dolg/raw/branch/main/result2.png" alt="result2" style="height:60px;"/>

## Factory Constructor

Create the operator via the following factory method

***image_embedding.dolg(img_size=512, input_dim=3, hidden_dim=1024, output_dim=2048)***

**Parameters:**

​   ***img_size***: *int*

​   Scaled input image size to extract embedding. The higher resolution would generate the more discriminateive feature but cost more time to calculate.  

​   ***input_dim***: *int*

​   The input dimension of DOLG module (equals pretrained cnn output dimension). 

​   ***hidden_dim***: *int*

​   The hidden dimension size, local feature branch output dimension. 

​   ***output_dim***: *int*

​   The output dimsion size, same as embedding size.

## 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.