模型:
helenai/microsoft-swin-tiny-patch4-window7-224-ov
这是转换为 OpenVINO 模型的 microsoft/swin-tiny-patch4-window7-224 ,用于加速推断。
对该模型进行推断的示例:
from optimum.intel.openvino import OVModelForImageClassification from transformers import AutoFeatureExtractor, pipeline model_id = "helenai/microsoft-swin-tiny-patch4-window7-224" model = OVModelForImageClassification.from_pretrained(model_id, compile=False) feature_extractor = AutoFeatureExtractor.from_pretrained(model_id) model.reshape(1,3, feature_extractor.size["height"], feature_extractor.size["width"]) model.compile() ov_pipe = pipeline("image-classification", model=model, feature_extractor=feature_extractor) image_url_or_path = "http://images.cocodataset.org/val2017/000000039769.jpg" ov_pipe(image_url_or_path)