Added shape docs for ThresholdedReLU layer from Keras (Kotlin#211)

https://keras.io/api/layers/activation_layers/threshold_relu/
dosier · Sep 29, 2022 · aa8f4f3 · aa8f4f3
1 parent e044a7f
commit aa8f4f3
Showing 1 changed file with 6 additions and 0 deletions.
diff --git a/...low/src/main/kotlin/org/jetbrains/kotlinx/dl/api/core/layer/activation/ThresholdedReLU.kt b/...low/src/main/kotlin/org/jetbrains/kotlinx/dl/api/core/layer/activation/ThresholdedReLU.kt
@@ -16,6 +16,12 @@ import org.tensorflow.op.Ops
  * f(x) = x,        if x > theta
  * f(x) = 0         otherwise
  * ```
+ *
+ * __Input shape:__  Arbitrary. Use the keyword argument `input_shape`
+ *                   (tuple of integers, does not include the samples axis)
+ *                   when using this layer as the first layer in a model.
+ * __Output shape:__ Same shape as the input.
+ *
  * @property [theta] Threshold value for activation.
  * @constructor Creates [ThresholdedReLU] object.
  *