|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- food101 |
|
tags: |
|
- openvino |
|
- int8 |
|
--- |
|
|
|
## [Vision Transformer (ViT)](https://huggingface.co/juliensimon/autotrain-food101-1471154050) quantized and exported to the OpenVINO IR. |
|
|
|
## Model Details |
|
**Model Description:** This ViT model fine-tuned on Food-101 was statically quantized and exported to the OpenVINO IR using [optimum](https://huggingface.co/docs/optimum/intel/optimization_ov). |
|
|
|
## Usage example |
|
|
|
You can use this model with Transformers *pipeline*. |
|
|
|
```python |
|
from transformers import pipeline, AutoFeatureExtractor |
|
from optimum.intel.openvino import OVModelForImageClassification |
|
|
|
model_id = "echarlaix/vit-food101-int8" |
|
model = OVModelForImageClassification.from_pretrained(model_id) |
|
feature_extractor = AutoFeatureExtractor.from_pretrained(model_id) |
|
pipe = pipeline("image-classification", model=model, feature_extractor=feature_extractor) |
|
outputs = pipe("http://farm2.staticflickr.com/1375/1394861946_171ea43524_z.jpg") |
|
``` |
