SAMBackbone
classkeras_hub.models.SAMBackbone(
image_encoder, prompt_encoder, mask_decoder, dtype=None, **kwargs
)
A backbone for the Segment Anything Model (SAM).
Arguments
keras_hub.models.ViTDetBackbone
. A feature extractor for
the input images.keras_hub.layers.SAMPromptEncoder
. A Keras layer to
compute embeddings for points, box, and mask prompt.keras_hub.layers.SAMMaskDecoder
. A Keras layer to
generate segmentation masks given the embeddings generated by the
backbone and the prompt encoder.Example
image_size=128
batch_size=2
input_data = {
"images": np.ones(
(batch_size, image_size, image_size, 3),
dtype="float32",
),
"points": np.ones((batch_size, 1, 2), dtype="float32"),
"labels": np.ones((batch_size, 1), dtype="float32"),
"boxes": np.ones((batch_size, 1, 2, 2), dtype="float32"),
"masks": np.zeros(
(batch_size, 0, image_size, image_size, 1)
),
}
image_encoder = keras_hub.models.ViTDetBackbone(
hidden_size=16,
num_layers=16,
intermediate_dim=16 * 4,
num_heads=16,
global_attention_layer_indices=[2, 5, 8, 11],
patch_size=16,
num_output_channels=8,
window_size=2,
image_shape=(image_size, image_size, 3),
)
prompt_encoder = keras_hub.layers.SAMPromptEncoder(
hidden_size=8,
image_embedding_size=(8, 8),
input_image_size=(
image_size,
image_size,
),
mask_in_channels=16,
)
mask_decoder = keras_hub.layers.SAMMaskDecoder(
num_layers=2,
hidden_size=8,
intermediate_dim=32,
num_heads=8,
embedding_dim=8,
num_multimask_outputs=3,
iou_head_depth=3,
iou_head_hidden_dim=8,
)
backbone = keras_hub.models.SAMBackbone(
image_encoder=image_encoder,
prompt_encoder=prompt_encoder,
mask_decoder=mask_decoder,
image_shape=(image_size, image_size, 3),
)
backbone(input_data)
from_preset
methodSAMBackbone.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:
'bert_base_en'
'kaggle://user/bert/keras/bert_base_en'
'hf://user/bert_base_en'
'./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
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,
)
Preset name | Parameters | Description |
---|---|---|
sam_base_sa1b | 93.74M | The base SAM model trained on the SA1B dataset. |
sam_large_sa1b | 641.09M | The large SAM model trained on the SA1B dataset. |
sam_huge_sa1b | 312.34M | The huge SAM model trained on the SA1B dataset. |