mindformers.models.vit.ViTForImageClassification

class mindformers.models.vit.ViTForImageClassification(config=None)

Vision Transformer with support for patch or hybrid CNN input stage. The supported model name could be selected from ViTConfig.show_support_list().

Args:

config (ViTConfig): the config of Vit model.

Examples:

>>> # input model name, load model and weights
>>> model_a = ViTForImageClassification.from_pretrained('vit_base_p16')
>>> # input config, load model without weights
>>> from mindformers import AutoConfig
>>> config = AutoConfig.from_pretrained('vit_base_p16')
>>> model_b = ViTForImageClassification(config)