public Conv2DTranspose(filters as Long, kernelSize as Tuple, strides as Long, padding as String = "valid", activation as String = "linear", useBias as Boolean = true, seed as Long = 1l)
Configures a layer whose input channel count is inferred on build.
| Parameter | Description |
|---|---|
filters | Positive output channel count. |
kernelSize | Positive (height, width) window. |
strides | Positive step for both spatial axes. |
padding | valid or same; odd padding goes to bottom/right. |
activation | linear, relu, sigmoid or tanh. |
useBias | Whether to train a zero-initialized bias. |
seed | Glorot initialization seed in [1, 2147483646]. |
layer = Conv2DTranspose<Float>(16, (3, 3), strides=2)