SigLIPBackbone model

[source]

SigLIPBackbone class

keras_hub.models.SigLIPBackbone(vision_encoder, text_encoder, dtype=None, **kwargs)

SigCLIP core network with hyperparameters.

This backbone implements the base architecture for the Sigmoid loss in the Language-Image Pre-training (SigLIP) model. Unlike standard contrastive learning with softmax normalization, the sigmoid loss operates solely on image-text pairs and does not require a global view of the pairwise similarities for normalization. It includes vision and text encoders. This backbone outputs the final logit scores corresponding to each image and token input.

The default constructor gives a fully customizable, randomly initialized SigLIP model with any number of layers, heads, and embedding dimensions. To load preset architectures and weights, use the from_preset constructor.

Arguments

• vision_encoder: The SigLIP vision encoder for encoding the input images.
• text_encoder: The SigLIP text encoder for encoding the input tokens.
• projection_dim: int. The size of the projection layer.
• dtype: string or keras.mixed_precision.DTypePolicy. The dtype to use for the models computations and weights. Note that some computations, such as softmax and layer normalization will always be done a float32 precision regardless of dtype.

Example

input_data = {
    "images": np.ones(shape=(1, 224, 224, 3), dtype="float32"),
    "token_ids": np.ones(shape=(1, 64), dtype="int32"),
}

# Pretrained SigLIP model.
model = keras_hub.models.SigLIPBackbone.from_preset(
    "siglip_base_patch16_224"
)
model(input_data)

# Randomly initialized SigLIP model with custom config.
vision_encoder = keras_hub.models.SigLIPVisionEncoder(
    patch_size=32,
    hidden_dim=768,
    num_layers=8,
    num_heads=8,
    intermediate_dim=2048,
    image_shape=(384, 384, 3),
)
text_encoder = keras_hub.models.SigLIPTextEncoder(
    vocabulary_size=32000,
    embedding_dim=768,
    hidden_dim=768,
    num_layers=8,
    num_heads=8,
    intermediate_dim=2048,
)
model = keras_hub.models.SigLIPBackbone(
    vision_encoder=vision_encoder,
    text_encoder=text_encoder,
)
model(input_data)

[source]

from_preset method

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

Instantiate a keras_hub.models.Backbone 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 a 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'

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

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

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, the weights will be loaded into the model architecture. If False, the weights will be randomly initialized.

Examples

# Load a Gemma backbone with pre-trained weights.
model = keras_hub.models.Backbone.from_preset(
    "gemma_2b_en",
)

# Load a Bert backbone with a pre-trained config and random weights.
model = keras_hub.models.Backbone.from_preset(
    "bert_base_en",
    load_weights=False,
)