clipcap/README.md

# Image Captioning with BLIP

*author: David Wang*


<br />



## Description

This operator generates the caption with [BLIP](https://arxiv.org/abs/2201.12086) which describes the content of the given image. This is an adaptation from [salesforce/BLIP](https://github.com/salesforce/BLIP).


<br />


## Code Example

Load an image from path './animals.jpg' to generate the caption. 

 *Write the pipeline in simplified style*:

```python
import towhee

towhee.glob('./animals.jpg') \
      .image_decode() \
      .image_captioning.blip(model_name='blip_base') \
      .select() \
      .show()
```
<img src="./cap.png" alt="result1" style="height:20px;"/>

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

```python
import towhee

towhee.glob['path']('./animals.jpg') \
      .image_decode['path', 'img']() \
      .image_captioning.blip['img', 'text'](model_name='blip_base') \
      .select['img', 'text']() \
      .show()
```
<img src="./tabular.png" alt="result2" style="height:60px;"/>


<br />



## Factory Constructor

Create the operator via the following factory method

***blip(model_name)***

**Parameters:**

​   ***model_name:*** *str*

​   The model name of BLIP. Supported model names: 
- blip_base     

<br />



## Interface

An image-text embedding operator takes a [towhee image](link/to/towhee/image/api/doc) as input and generate the correspoing caption.


**Parameters:**

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

​  The image to generate embedding.	



**Returns:** *str*

​   The caption generated by model.