task.json

{
    "module": "keras_hub.src.models.vit.vit_image_classifier",
    "class_name": "ViTImageClassifier",
    "config": {
        "backbone": {
            "module": "keras_hub.src.models.vit.vit_backbone",
            "class_name": "ViTBackbone",
            "config": {
                "name": "vi_t_backbone",
                "trainable": true,
                "image_shape": [
                    384,
                    384,
                    3
                ],
                "patch_size": 32,
                "num_layers": 24,
                "num_heads": 16,
                "hidden_dim": 1024,
                "mlp_dim": 4096,
                "dropout_rate": 0.0,
                "attention_dropout": 0.0,
                "layer_norm_epsilon": 1e-06,
                "use_mha_bias": true,
                "use_mlp_bias": true
            },
            "registered_name": "keras_hub>ViTBackbone"
        },
        "preprocessor": {
            "module": "keras_hub.src.models.vit.vit_image_classifier_preprocessor",
            "class_name": "ViTImageClassifierPreprocessor",
            "config": {
                "name": "vi_t_image_classifier_preprocessor",
                "trainable": true,
                "dtype": {
                    "module": "keras",
                    "class_name": "DTypePolicy",
                    "config": {
                        "name": "float32"
                    },
                    "registered_name": null
                },
                "image_converter": {
                    "module": "keras_hub.src.models.vit.vit_image_converter",
                    "class_name": "ViTImageConverter",
                    "config": {
                        "name": "vi_t_image_converter",
                        "trainable": true,
                        "dtype": {
                            "module": "keras",
                            "class_name": "DTypePolicy",
                            "config": {
                                "name": "float32"
                            },
                            "registered_name": null
                        },
                        "image_size": [
                            384,
                            384
                        ],
                        "scale": 0.00392156862745098,
                        "offset": null,
                        "interpolation": "bilinear",
                        "crop_to_aspect_ratio": true,
                        "norm_mean": [
                            0.5,
                            0.5,
                            0.5
                        ],
                        "norm_std": [
                            0.5,
                            0.5,
                            0.5
                        ]
                    },
                    "registered_name": "keras_hub>ViTImageConverter"
                },
                "config_file": "preprocessor.json"
            },
            "registered_name": "keras_hub>ViTImageClassifierPreprocessor"
        },
        "name": "vi_t_image_classifier",
        "num_classes": 1000,
        "pooling": "token",
        "activation": null,
        "dropout": 0.0,
        "intermediate_dim": null
    },
    "registered_name": "keras_hub>ViTImageClassifier"
}