inceptionresnetv1/README.md

# Inception-ResNet v1 Face Embedding Operator

*author: David Wang*


<br />



## Description

This operator extracts embedding vector from facial image using [Inception-ResNet](https://arxiv.org/pdf/1602.07261.pdf). The implementation is an adaptation from [timesler/facenet-pytorch](https://github.com/timesler/facenet-pytorch). 


<br />


## Code Example

Extract face image embedding from './img.png'. 

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

```python
from towhee.dc2 import pipe, ops, DataCollection

p = (
    pipe.input('path')
        .map('path', 'img', ops.image_decode())
        .map('img', 'vec', ops.face_embedding.inceptionresnetv1())
        .output('img', 'vec')
)

DataCollection(p('img.png')).show()
```

<img src="https://towhee.io/face-embedding/inceptionresnetv1/raw/branch/main/result.png" alt="result" style="height:60px;"/>


<br />



## Factory Constructor

Create the operator via the following factory method:

***face_embedding.inceptionresnetv1(image_size = 160)***

**Parameters:**

***image_size:*** *int*

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

supported types: `int`, default is 160.


<br />


## Interface

A face embedding operator takes a face image as input. It extracts the embedding in ndarray.

**Parameters:**

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

​	The input image.

**Returns:** *numpy.ndarray*

​	The extracted image embedding.