# Pipeline: Image Embedding using resnet50

Authors: Filip

## Overview

The pipeline is used to **extract the feature vector of a given image**. It uses the the resnet50 model from Ross Wightman's [`timm`](https://github.com/rwightman/pytorch-image-models) to generate the vector.

## Interface

**Input Arguments:**

- img_path:
  - the input image path
  - supported types: `str`

**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`
  - shape: (1, 2048)

## 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

>>> img_path = 'path/to/your/image'
>>> embedding_pipeline = pipeline('towhee/image-embedding-resnet50')
>>> embedding = embedding_pipeline(img_path)
```