image-embedding-resnet50/README.md

# Pipeline: Image Embedding using Resnet50

Authors: derekdqc, shiyu22

## Overview

The pipeline is used to **extract the feature vector of a given image**. It first normalizes the image and then uses Resnet50 model to generate the vector.

## Interface

**Input Arguments:**

- image:
  - the input image to be encoded
  - supported types: `PIL.Image`

**Pipeline Output:**

The pipeline returns a tuple `Tuple[('feature_vector', numpy.ndarray)]` containing following fields:

- feature_vector:
  - the embedding of input image
  - data type: `numpy.ndarray`

## How to use

1. Install [Towhee](https://github.com/towhee-io/towhee)

```bash
$ pip3 install towhee
```

> You can refer to [Getting Started with Towhee](https://towhee.io/) for more details. If you have any questions, you can [submit an issue to the towhee repository](https://github.com/towhee-io/towhee/issues).

2. Run it with Towhee

```python
>>> from towhee import pipeline
>>> from PIL import Image

>>> img = Image.open('path/to/your/image') # for example, './test.jpg'
>>> embedding_pipeline = pipeline('towhee/image-embedding-resnet50')
>>> embedding = embedding_pipeline(img)
```

## How it works

This pipeline includes two main operators: [transform image](https://hub.towhee.io/towhee/transform-image-operator-class) (implemented as [towhee/transform-image](https://hub.towhee.io/towhee/transform-image)) and [image embedding](https://hub.towhee.io/towhee/image-embedding-operator-class) (implemented as [towhee/resnet50-image-embedding](https://hub.towhee.io/towhee/resnet50-image-embedding)). The transform image op will first convert the original image into a normalized format, such as with 512x512 resolutions. Then, the normalized image will be encoded via image embedding op, and finally we get a feature vector of the given image.

> Refer [Towhee architecture](https://github.com/towhee-io/towhee#towhee-architecture) for basic concepts in Towhee: pipeline, operator, dataframe.

![img](./readme_res/pipeline.png)