许可协议：apache-2.0
数据集：

• food101
  标签：
• openvino
• int8

视觉变换器（ViT）量化并导出为OpenVINO IR格式

模型详情

模型描述： 该基于Food-101微调的ViT模型通过optimum工具进行了静态量化，并导出为OpenVINO中间表示格式。

使用示例

可通过Transformers的pipeline调用本模型：

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")