README.md

---
tags:
- vision
- zero-shot-image-classification
- endpoints-template
library_name: generic
---

# Fork of [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) for a `zero-sho-image-classification` Inference endpoint.

This repository implements a `custom` task for `zero-shot-image-classification` for 🤗 Inference Endpoints. The code for the customized pipeline is in the [pipeline.py](https://huggingface.co/philschmid/clip-zero-shot-image-classification/blob/main/pipeline.py).

To use deploy this model a an Inference Endpoint you have to select `Custom` as task to use the `pipeline.py` file. -> _double check if it is selected_

### expected Request payload

```json
{
  "image": "/9j/4AAQSkZJRgABAQEBLAEsAAD/2wBDAAMCAgICAgMC....", // base64 image as bytes
  "candiates":["sea","palace","car","ship"]
}
```

below is an example on how to run a request using Python and `requests`.

## Run Request 

1. prepare an image. 

```bash
!wget https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.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, candiates: List[str] = None):
    with open(path_to_image, "rb") as i:
        b64 = base64.b64encode(i.read())

    payload = {"inputs": {"image": b64.decode("utf-8"), "candiates": candiates}}
    response = r.post(
        ENDPOINT_URL, headers={"Authorization": f"Bearer {HF_TOKEN}"}, json=payload
    )
    return response.json()


prediction = predict(
    path_to_image="palace.jpg", candiates=["sea", "palace", "car", "ship"]
)
```

expected output

```python
[{'label': 'palace', 'score': 0.9996134638786316},
 {'label': 'car', 'score': 0.0002602009626571089},
 {'label': 'ship', 'score': 0.00011758189066313207},
 {'label': 'sea', 'score': 8.666840585647151e-06}]
```