Keras
Keras 3 API documentation
KerasCV
Models
Backbones
EfficientNet Lite backbones

EfficientNet Lite backbones

source

EfficientNetLiteBackbone class 

keras_cv.models.EfficientNetLiteBackbone(
    include_rescaling,
    width_coefficient,
    depth_coefficient,
    stackwise_kernel_sizes,
    stackwise_num_repeats,
    stackwise_input_filters,
    stackwise_output_filters,
    stackwise_expansion_ratios,
    stackwise_strides,
    dropout_rate=0.2,
    drop_connect_rate=0.2,
    depth_divisor=8,
    input_shape=(None, None, 3),
    input_tensor=None,
    activation="relu6",
    **kwargs
)

Instantiates the EfficientNetLite architecture using given scaling coefficients.

Reference

Arguments

  • include_rescaling: whether to rescale the inputs. If set to True, inputs will be passed through a Rescaling(1/255.0) layer.
  • width_coefficient: float, scaling coefficient for network width.
  • depth_coefficient: float, scaling coefficient for network depth.
  • dropout_rate: float, dropout rate before final classifier layer.
  • drop_connect_rate: float, dropout rate at skip connections. The default value is set to 0.2.
  • depth_divisor: integer, a unit of network width. The default value is set to 8.
  • activation: activation function.
  • input_shape: optional shape tuple, It should have exactly 3 inputs channels.
  • input_tensor: optional Keras tensor (i.e. output of keras.layers.Input()) to use as image input for the model.

Example

# Construct an EfficientNetLite from a preset:
efficientnet = models.EfficientNetLiteBackbone.from_preset(
    "efficientnetlite_b0"
)
images = np.ones((1, 256, 256, 3))
outputs = efficientnet.predict(images)
# Alternatively, you can also customize the EfficientNetLite architecture:
model = EfficientNetLiteBackbone(
    stackwise_kernel_sizes=[3, 3, 5, 3, 5, 5, 3],
    stackwise_num_repeats=[1, 2, 2, 3, 3, 4, 1],
    stackwise_input_filters=[32, 16, 24, 40, 80, 112, 192],
    stackwise_output_filters=[16, 24, 40, 80, 112, 192, 320],
    stackwise_expansion_ratios=[1, 6, 6, 6, 6, 6, 6],
    stackwise_strides=[1, 2, 2, 2, 1, 2, 1],
    width_coefficient=1.0,
    depth_coefficient=1.0,
    include_rescaling=False,
)
images = np.ones((1, 256, 256, 3))
outputs = model.predict(images)

source

from_preset method 

EfficientNetLiteBackbone.from_preset()

Instantiate EfficientNetLiteBackbone model from preset config and weights.

Arguments

  • preset: string. Must be one of “efficientnetlite_b0”, “efficientnetlite_b1”, “efficientnetlite_b2”, “efficientnetlite_b3”, “efficientnetlite_b4”. If looking for a preset with pretrained weights, choose one of “”.
  • load_weights: Whether to load pre-trained weights into model. Defaults to None, which follows whether the preset has pretrained weights available.

Examples

# Load architecture and weights from preset
model = keras_cv.models.EfficientNetLiteBackbone.from_preset(
    "",
)
# Load randomly initialized model from preset architecture with weights
model = keras_cv.models.EfficientNetLiteBackbone.from_preset(
    "",
    load_weights=False,
Preset nameParametersDescription
efficientnetlite_b03.41MEfficientNet B-style architecture with 7 convolutional blocks. This B-style model has width_coefficient=1.0 and depth_coefficient=1.0.
efficientnetlite_b14.19MEfficientNet B-style architecture with 7 convolutional blocks. This B-style model has width_coefficient=1.0 and depth_coefficient=1.1.
efficientnetlite_b24.87MEfficientNet B-style architecture with 7 convolutional blocks. This B-style model has width_coefficient=1.1 and depth_coefficient=1.2.
efficientnetlite_b36.99MEfficientNet B-style architecture with 7 convolutional blocks. This B-style model has width_coefficient=1.2 and depth_coefficient=1.4.
efficientnetlite_b411.84MEfficientNet B-style architecture with 7 convolutional blocks. This B-style model has width_coefficient=1.4 and depth_coefficient=1.8.

source

EfficientNetLiteB0Backbone class 

keras_cv.models.EfficientNetLiteB0Backbone(
    include_rescaling,
    width_coefficient,
    depth_coefficient,
    stackwise_kernel_sizes,
    stackwise_num_repeats,
    stackwise_input_filters,
    stackwise_output_filters,
    stackwise_expansion_ratios,
    stackwise_strides,
    dropout_rate=0.2,
    drop_connect_rate=0.2,
    depth_divisor=8,
    input_shape=(None, None, 3),
    input_tensor=None,
    activation="relu6",
    **kwargs
)

Instantiates the EfficientNetLiteB0 architecture.

Reference

Arguments

  • include_rescaling: bool, whether to rescale the inputs. If set to True, inputs will be passed through a Rescaling(1/255.0) layer.
  • input_shape: optional shape tuple, defaults to (None, None, 3).
  • input_tensor: optional Keras tensor (i.e. output of layers.Input()) to use as image input for the model.

Example

input_data = np.ones(shape=(8, 224, 224, 3))
# Randomly initialized backbone
model = EfficientNetLiteB0Backbone()
output = model(input_data)

source

EfficientNetLiteB1Backbone class 

keras_cv.models.EfficientNetLiteB1Backbone(
    include_rescaling,
    width_coefficient,
    depth_coefficient,
    stackwise_kernel_sizes,
    stackwise_num_repeats,
    stackwise_input_filters,
    stackwise_output_filters,
    stackwise_expansion_ratios,
    stackwise_strides,
    dropout_rate=0.2,
    drop_connect_rate=0.2,
    depth_divisor=8,
    input_shape=(None, None, 3),
    input_tensor=None,
    activation="relu6",
    **kwargs
)

Instantiates the EfficientNetLiteB1 architecture.

Reference

Arguments

  • include_rescaling: bool, whether to rescale the inputs. If set to True, inputs will be passed through a Rescaling(1/255.0) layer.
  • input_shape: optional shape tuple, defaults to (None, None, 3).
  • input_tensor: optional Keras tensor (i.e. output of layers.Input()) to use as image input for the model.

Example

input_data = np.ones(shape=(8, 224, 224, 3))
# Randomly initialized backbone
model = EfficientNetLiteB1Backbone()
output = model(input_data)

source

EfficientNetLiteB2Backbone class 

keras_cv.models.EfficientNetLiteB2Backbone(
    include_rescaling,
    width_coefficient,
    depth_coefficient,
    stackwise_kernel_sizes,
    stackwise_num_repeats,
    stackwise_input_filters,
    stackwise_output_filters,
    stackwise_expansion_ratios,
    stackwise_strides,
    dropout_rate=0.2,
    drop_connect_rate=0.2,
    depth_divisor=8,
    input_shape=(None, None, 3),
    input_tensor=None,
    activation="relu6",
    **kwargs
)

Instantiates the EfficientNetLiteB2 architecture.

Reference

Arguments

  • include_rescaling: bool, whether to rescale the inputs. If set to True, inputs will be passed through a Rescaling(1/255.0) layer.
  • input_shape: optional shape tuple, defaults to (None, None, 3).
  • input_tensor: optional Keras tensor (i.e. output of layers.Input()) to use as image input for the model.

Example

input_data = np.ones(shape=(8, 224, 224, 3))
# Randomly initialized backbone
model = EfficientNetLiteB2Backbone()
output = model(input_data)

source

EfficientNetLiteB3Backbone class 

keras_cv.models.EfficientNetLiteB3Backbone(
    include_rescaling,
    width_coefficient,
    depth_coefficient,
    stackwise_kernel_sizes,
    stackwise_num_repeats,
    stackwise_input_filters,
    stackwise_output_filters,
    stackwise_expansion_ratios,
    stackwise_strides,
    dropout_rate=0.2,
    drop_connect_rate=0.2,
    depth_divisor=8,
    input_shape=(None, None, 3),
    input_tensor=None,
    activation="relu6",
    **kwargs
)

Instantiates the EfficientNetLiteB3 architecture.

Reference

Arguments

  • include_rescaling: bool, whether to rescale the inputs. If set to True, inputs will be passed through a Rescaling(1/255.0) layer.
  • input_shape: optional shape tuple, defaults to (None, None, 3).
  • input_tensor: optional Keras tensor (i.e. output of layers.Input()) to use as image input for the model.

Example

input_data = np.ones(shape=(8, 224, 224, 3))
# Randomly initialized backbone
model = EfficientNetLiteB3Backbone()
output = model(input_data)

source

EfficientNetLiteB4Backbone class 

keras_cv.models.EfficientNetLiteB4Backbone(
    include_rescaling,
    width_coefficient,
    depth_coefficient,
    stackwise_kernel_sizes,
    stackwise_num_repeats,
    stackwise_input_filters,
    stackwise_output_filters,
    stackwise_expansion_ratios,
    stackwise_strides,
    dropout_rate=0.2,
    drop_connect_rate=0.2,
    depth_divisor=8,
    input_shape=(None, None, 3),
    input_tensor=None,
    activation="relu6",
    **kwargs
)

Instantiates the EfficientNetLiteB4 architecture.

Reference

Arguments

  • include_rescaling: bool, whether to rescale the inputs. If set to True, inputs will be passed through a Rescaling(1/255.0) layer.
  • input_shape: optional shape tuple, defaults to (None, None, 3).
  • input_tensor: optional Keras tensor (i.e. output of layers.Input()) to use as image input for the model.

Example

input_data = np.ones(shape=(8, 224, 224, 3))
# Randomly initialized backbone
model = EfficientNetLiteB4Backbone()
output = model(input_data)