mindformers.models.mae.ViTMAEProcessor¶

class mindformers.models.mae.ViTMAEProcessor(image_processor=None, return_tensors='ms')[源代码]¶

ViTMAEProcessor, consists of a feature extractor (BaseFeatureEXtractor) for image input.

实际案例

>>> from mindformers import MindFormerBook
>>> from mindformers.models import ViTMAEProcessor
>>> yaml_path = os.path.join(MindFormerBook.get_project_path(), "configs",
...                          "mae", "model_config", "mae_vit_base_p16.yaml")
>>> # build ViTMAEProcessor from pretrained
>>> pro_a = ViTMAEProcessor.from_pretrained('mae_vit_base_p16')
>>> # build ViTMAEProcessor from config
>>> pro_b = ViTMAEProcessor.from_pretrained(yaml_path)