tfm.vision.backbones.SpineNetMobile

Creates a Mobile SpineNet family model.

tfm.vision.backbones.SpineNetMobile(
    input_specs: tf.keras.layers.InputSpec = tf.keras.layers.InputSpec(shape=[None, None, None, 3]),
    min_level: int = 3,
    max_level: int = 7,
    block_specs: List[BlockSpec] = build_block_specs(),
    endpoints_num_filters: int = 256,
    se_ratio: float = 0.2,
    block_repeats: int = 1,
    filter_size_scale: float = 1.0,
    expand_ratio: int = 6,
    init_stochastic_depth_rate=0.0,
    kernel_initializer: str = 'VarianceScaling',
    kernel_regularizer: Optional[tf.keras.regularizers.Regularizer] = None,
    bias_regularizer: Optional[tf.keras.regularizers.Regularizer] = None,
    activation: str = 'relu',
    use_sync_bn: bool = False,
    norm_momentum: float = 0.99,
    norm_epsilon: float = 0.001,
    use_keras_upsampling_2d: bool = False,
    **kwargs
)

This implements
[1] Xianzhi Du, Tsung-Yi Lin, Pengchong Jin, Golnaz Ghiasi, Mingxing Tan, Yin Cui, Quoc V. Le, Xiaodan Song.
SpineNet	Learning Scale-Permuted Backbone for Recognition and Localization. (https://arxiv.org/abs/1912.05027). [2] Xianzhi Du, Tsung-Yi Lin, Pengchong Jin, Yin Cui, Mingxing Tan, Quoc Le, Xiaodan Song. Efficient Scale-Permuted Backbone with Learned Resource Distribution. (https://arxiv.org/abs/2010.11426).

Args
input_specs	A tf.keras.layers.InputSpec of the input tensor.
min_level	An int of min level for output mutiscale features.
max_level	An int of max level for output mutiscale features.
block_specs	The block specifications for the SpineNet model discovered by NAS.
endpoints_num_filters	An int of feature dimension for the output endpoints.
se_ratio	A float of Squeeze-and-Excitation ratio.
block_repeats	An int of number of blocks contained in the layer.
filter_size_scale	A float of multiplier for the filters (number of channels) for all convolution ops. The value must be greater than zero. Typical usage will be to set this value in (0, 1) to reduce the number of parameters or computation cost of the model.
expand_ratio	An integer of expansion ratios for inverted bottleneck blocks.
init_stochastic_depth_rate	A float of initial stochastic depth rate.
kernel_initializer	A str for kernel initializer of convolutional layers.
kernel_regularizer	A tf.keras.regularizers.Regularizer object for Conv2D. Default to None.
bias_regularizer	A tf.keras.regularizers.Regularizer object for Conv2D. Default to None.
activation	A str name of the activation function.
use_sync_bn	If True, use synchronized batch normalization.
norm_momentum	A float of normalization momentum for the moving average.
norm_epsilon	A small float added to variance to avoid dividing by zero.
use_keras_upsampling_2d	If True, use keras UpSampling2D layer.
**kwargs	Additional keyword arguments to be passed.

Attributes
output_specs	A dict of {level: TensorShape} pairs for the model output.

Methods

call

call(
    inputs, training=None, mask=None
)

Calls the model on new inputs and returns the outputs as tensors.

In this case call() just reapplies all ops in the graph to the new inputs (e.g. build a new computational graph from the provided inputs).

Note: This method should not be called directly. It is only meant to be overridden when subclassing tf.keras.Model. To call a model on an input, always use the __call__() method, i.e. model(inputs), which relies on the underlying call() method.

Args
inputs	Input tensor, or dict/list/tuple of input tensors.
training	Boolean or boolean scalar tensor, indicating whether to run the Network in training mode or inference mode.
mask	A mask or list of masks. A mask can be either a boolean tensor or None (no mask). For more details, check the guide here.

Returns
A tensor if there is a single output, or a list of tensors if there are more than one outputs.