tfm.vision.layers.BottleneckResidualInner

Creates a single inner block of a bottleneck.

tfm.vision.layers.BottleneckResidualInner(
    filters: int,
    strides: int,
    kernel_initializer: Union[str, Callable[..., tf_keras.initializers.Initializer]] = 'VarianceScaling',
    kernel_regularizer: Optional[tf_keras.regularizers.Regularizer] = None,
    activation: Union[str, Callable[..., tf.Tensor]] = 'relu',
    use_sync_bn: bool = False,
    norm_momentum: float = 0.99,
    norm_epsilon: float = 0.001,
    batch_norm_first: bool = True,
    **kwargs
)

This corresponds to F/G functions in the RevNet paper: Aidan N. Gomez, Mengye Ren, Raquel Urtasun, Roger B. Grosse. The Reversible Residual Network: Backpropagation Without Storing Activations. (https://arxiv.org/pdf/1707.04585.pdf)

filters An int number of filters for first 2 convolutions. Last Last, and thus the number of output channels from the bottlneck block is 4*filters
strides An int of stride size for convolution for the residual block.
kernel_initializer A str or tf_keras.initializers.Initializer instance for convolutional layers.
kernel_regularizer A tf_keras.regularizers.Regularizer for Conv2D.
activation A str or callable instance of the activation function.
use_sync_bn A bool. If True, use synchronized batch normalization.
norm_momentum A float of normalization momentum for the moving average.
norm_epsilon A float added to variance to avoid dividing by zero.
batch_norm_first A bool of whether to apply activation and batch norm before conv.
**kwargs Additional keyword arguments to be passed.

Methods

call

View source

call(
    inputs: tf.Tensor, training: Optional[bool] = None
) -> tf.Tensor

This is where the layer's logic lives.

The call() method may not create state (except in its first invocation, wrapping the creation of variables or other resources in tf.init_scope()). It is recommended to create state, including tf.Variable instances and nested Layer instances, in __init__(), or in the build() method that is called automatically before call() executes for the first time.

Args
inputs Input tensor, or dict/list/tuple of input tensors. The first positional inputs argument is subject to special rules:

  • inputs must be explicitly passed. A layer cannot have zero arguments, and inputs cannot be provided via the default value of a keyword argument.
  • NumPy array or Python scalar values in inputs get cast as tensors.
  • TF-Keras mask metadata is only collected from inputs.
  • Layers are built (build(input_shape) method) using shape info from inputs only.
  • input_spec compatibility is only checked against inputs.
  • Mixed precision input casting is only applied to inputs. If a layer has tensor arguments in *args or **kwargs, their casting behavior in mixed precision should be handled manually.
  • The SavedModel input specification is generated using inputs only.
  • Integration with various ecosystem packages like TFMOT, TFLite, TF.js, etc is only supported for inputs and not for tensors in positional and keyword arguments.
*args Additional positional arguments. May contain tensors, although this is not recommended, for the reasons above.
**kwargs Additional keyword arguments. May contain tensors, although this is not recommended, for the reasons above. The following optional keyword arguments are reserved:
  • training: Boolean scalar tensor of Python boolean indicating whether the call is meant for training or inference.
  • mask: Boolean input mask. If the layer's call() method takes a mask argument, its default value will be set to the mask generated for inputs by the previous layer (if input did come from a layer that generated a corresponding mask, i.e. if it came from a TF-Keras layer with masking support).

    • Returns
    A tensor or list/tuple of tensors.