Layers
Custom layers used in our models
Conv2DNormalization
paz.models.layers.Conv2DNormalization(scale, axis=3)
Normalization layer as described in ParseNet paper.
Arguments
- scale: Float determining how much to scale the features.
- axis: Integer specifying axis of image channels.
Returns
Feature map tensor normalized with an L2 norm and then scaled.
References
SubtractScalar
paz.models.layers.SubtractScalar(constant)
Subtracts scalar value to tensor.
Arguments
- constant: Float. Value to be subtracted to all tensor values.
ExpectedValue2D
paz.models.layers.ExpectedValue2D(axes=[2, 3])
Calculates the expected value along ''axes''.
Arguments
- axes: List of integers. Axes for which the expected value will be calculated.
ExpectedDepth
paz.models.layers.ExpectedDepth(axes=[2, 3])
Calculates the expected depth along ''axes''. This layer takes two inputs. First input is a depth estimation tensor. Second input is a probability map of the keypoints. It multiplies both values and calculates the expected depth.
Arguments
- axes: List of integers. Axes for which the expected value will be calculated.
ReduceMean
paz.models.layers.ReduceMean(axes=[1, 2], keepdims=True)
Wraps tensorflow's reduce_mean
function into a keras layer.
Arguments
- axes: List of integers. Axes along which mean is to be calculated.
- keepdims: Bool, whether to presere the dimension or not.
Sigmoid
paz.models.layers.Sigmoid()
Wraps tensorflow's sigmoid
function into a keras layer.
Add
paz.models.layers.Add()
Wraps tensorflow's add
function into a keras layer.