vit-food101-int8 / README.md
echarlaix's picture
echarlaix HF staff
Upload model
6dc21d1
metadata
license: apache-2.0
datasets:
  - food101
tags:
  - openvino
  - int8

Vision Transformer (ViT) 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.

Usage example

You can use this model with Transformers pipeline.

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")