---
tags:
- clip
- image-classification
- endpoints-template
library_name: generic
---

# Fork of [Geonmo/laion-aesthetic-predictor](https://huggingface.co/spaces/Geonmo/laion-aesthetic-predictor) for an Image Aesthetic Predictor).

This repository implements a `custom` task for `Geonmo/laion-aesthetic-predictor` for 🤗 Inference Endpoints. The code for the customized handler is in the [handler.py](https://huggingface.co/philschmid/laion-asthetic-endpoint/tree/main/handler.py).

## Test Handler locally. 

This model & handker can be tested locally using the [
hf-endpoints-emulator](https://github.com/huggingface/hf-endpoints-emulator).


1. Clone the repository and install the requirements. 

```bash
git lfs install
git clone https://huggingface.co/philschmid/laion-asthetic-endpoint

cd laion-asthetic-endpoint
pip install -r requirements.txt
```
2. Install `hf-endpoints-emulator`

```bash
pip install hf-endpoints-emulator
```

3. Run the emulator

```bash
hf-endpoints-emulator --handler handler.py
```

4. Test the endpoint and send request

```bash
curl --request POST \
  --url http://localhost \
  --header 'Content-Type: image/jpg' \
  --data-binary '@example1.jpg'
```


## Run Request 

The endpoint expects the image to be served as `binary`. Below is an curl and python example

#### cURL 

1. get image 

```bash
wget https://fki.tic.heia-fr.ch/static/img/a01-122-02-00.jpg -O test.jpg
```

2. send cURL request

```bash
curl --request POST \
  --url https://{ENDPOINT}/ \
  --header 'Content-Type: image/jpg' \
  --header 'Authorization: Bearer {HF_TOKEN}' \
  --data-binary '@test.jpg'
```

3. the expected output

```json
{"text": "INDLUS THE"}
```

#### Python 


1. get image 

```bash
wget https://fki.tic.heia-fr.ch/static/img/a01-122-02-00.jpg -O test.jpg
```

2. run request

```python
import json
from typing import List
import requests as r
import base64

ENDPOINT_URL=""
HF_TOKEN=""

def predict(path_to_image:str=None):
    with open(path_to_image, "rb") as i:
      b = i.read()
    headers= {
        "Authorization": f"Bearer {HF_TOKEN}",
        "Content-Type": "image/jpeg" # content type of image
    }
    response = r.post(ENDPOINT_URL, headers=headers, data=b)
    return response.json()

prediction = predict(path_to_image="test.jpg")

prediction
```

expected output

```python
{"text": "INDLUS THE"}
```