SwinTransformerImageClassifier model

[source]

SwinTransformerImageClassifier class

keras_hub.models.SwinTransformerImageClassifier(
    backbone,
    num_classes,
    preprocessor=None,
    activation=None,
    dropout=0.0,
    head_dtype=None,
    **kwargs
)

Swin Transformer image classification task.

SwinTransformerImageClassifier tasks wrap a keras_hub.models.SwinTransformerBackbone and a keras_hub.models.Preprocessor to create a model that can be used for image classification. The classifier pools the backbone output over the sequence dimension and applies a dense classification head.

To fine-tune with fit(), pass a dataset containing tuples of (x, y) labels where x is an image and y is an integer from [0, num_classes).

Arguments

• backbone: A keras_hub.models.SwinTransformerBackbone instance or a keras.Model.
• num_classes: int. The number of classes to predict.
• preprocessor: None, a keras_hub.models.Preprocessor instance, a keras.Layer instance, or a callable. If None no preprocessing will be applied to the inputs.
• activation: None, str, or callable. The activation function to use on the Dense layer. Set activation=None to return the output logits. Defaults to None.
• head_dtype: None, str, or keras.mixed_precision.DTypePolicy. The dtype to use for the classification head's computations and weights.
• dropout: float. Dropout rate applied before the classification head. Defaults to 0.0.

Examples

Call predict() to run inference.

images = np.random.randint(0, 256, size=(2, 224, 224, 3))
classifier = keras_hub.models.SwinTransformerImageClassifier.from_preset(
    "swin_tiny_patch4_window7_224"
)
classifier.predict(images)

Call fit() on a single batch.

images = np.random.randint(0, 256, size=(2, 224, 224, 3))
labels = [0, 3]
classifier = keras_hub.models.SwinTransformerImageClassifier.from_preset(
    "swin_tiny_patch4_window7_224"
)
classifier.fit(x=images, y=labels, batch_size=2)

Custom backbone.

images = np.random.randint(0, 256, size=(2, 224, 224, 3))
labels = [0, 3]
backbone = keras_hub.models.SwinTransformerBackbone(
    image_shape=(224, 224, 3),
    embed_dim=96,
    depths=(2, 2, 6, 2),
    num_heads=(3, 6, 12, 24),
    window_size=7,
)
classifier = keras_hub.models.SwinTransformerImageClassifier(
    backbone=backbone,
    num_classes=4,
)
classifier.fit(x=images, y=labels, batch_size=2)

[source]

from_preset method

SwinTransformerImageClassifier.from_preset(preset, load_weights=True, **kwargs)

Instantiate a keras_hub.models.Task from a model preset.

A preset is a directory of configs, weights and other file assets used to save and load a pre-trained model. The preset can be passed as one of:

1. a built-in preset identifier like 'bert_base_en'
2. a Kaggle Models handle like 'kaggle://user/bert/keras/bert_base_en'
3. a Hugging Face handle like 'hf://user/bert_base_en'
4. a path to a local preset directory like './bert_base_en'

For any Task subclass, you can run cls.presets.keys() to list all built-in presets available on the class.

This constructor can be called in one of two ways. Either from a task specific base class like keras_hub.models.CausalLM.from_preset(), or from a model class like keras_hub.models.BertTextClassifier.from_preset(). If calling from the a base class, the subclass of the returning object will be inferred from the config in the preset directory.

Arguments

• preset: string. A built-in preset identifier, a Kaggle Models handle, a Hugging Face handle, or a path to a local directory.
• load_weights: bool. If True, saved weights will be loaded into the model architecture. If False, all weights will be randomly initialized.

Examples

# Load a Gemma generative task.
causal_lm = keras_hub.models.CausalLM.from_preset(
    "gemma_2b_en",
)

# Load a Bert classification task.
model = keras_hub.models.TextClassifier.from_preset(
    "bert_base_en",
    num_classes=2,
)

backbone property

keras_hub.models.SwinTransformerImageClassifier.backbone

A keras_hub.models.Backbone model with the core architecture.

preprocessor property

keras_hub.models.SwinTransformerImageClassifier.preprocessor

A keras_hub.models.Preprocessor layer used to preprocess input.