README.md

---
title: "ViT-Tiny"
subtitle: "Vision transformer image classifier"
category: "Vision AI"
model_type:
  - "Classification"
license: apache-2.0
code: "https://huggingface.co/timm/vit_tiny_patch16_224.augreg_in21k"
tags:
  - robotics-ai-suite
  - vision-ai
  - "chipset:ptl"
thumbnail: assets/thumbnail.png
---

ViT-Tiny image classification model, a [Geti™](https://github.com/open-edge-platform/geti)
build of [ViT-Tiny](https://huggingface.co/timm/vit_tiny_patch16_224.augreg_in21k)
converted to OpenVINO™ IR with FP16 weights. It maps an input image to class
scores. Model weights are hosted in the source repository
[OpenVINO/vit_tiny_cls-fp16-ov](https://huggingface.co/OpenVINO/vit_tiny_cls-fp16-ov).

# How to Use

1. Install required packages:

```sh
pip install openvino-model-api[huggingface]
```

2. Run model inference:

```python
import cv2
from model_api.models import Model
from model_api.visualizer import Visualizer

model = Model.from_pretrained("OpenVINO/vit_tiny_cls-fp16-ov")
image = cv2.imread("image.jpg")
result = model(image)
vis = Visualizer().render(image, result)
cv2.imwrite("output.jpg", vis)
```

# Legal information

The original model is distributed under the
[Apache-2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md)
license. More details can be found in the
[original model card](https://huggingface.co/timm/vit_tiny_patch16_224.augreg_in21k).