keras/deit_tiny_distilled_patch16_224_imagenet

This is a DeiT model uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends. This model is related to a ImageClassifier task.

Model config:

• name: dei_t_backbone
• trainable: True
• image_shape: [224, 224, 3]
• patch_size: [16, 16]
• num_layers: 12
• num_heads: 3
• hidden_dim: 192
• intermediate_dim: 768
• dropout_rate: 0.0
• attention_dropout: 0.0
• layer_norm_epsilon: 1e-12
• use_mha_bias: True

This model card has been generated automatically and should be completed by the model author. See Model Cards documentation for more information.