Added shape docs for MaxPool1D layer from Keras (Kotlin#211)

https://keras.io/api/layers/pooling_layers/max_pooling1d/
dosier · Sep 29, 2022 · 4ac2bcb · 4ac2bcb
1 parent b66ac7f
commit 4ac2bcb
Showing 1 changed file with 4 additions and 0 deletions.
diff --git a/tensorflow/src/main/kotlin/org/jetbrains/kotlinx/dl/api/core/layer/pooling/MaxPool1D.kt b/tensorflow/src/main/kotlin/org/jetbrains/kotlinx/dl/api/core/layer/pooling/MaxPool1D.kt
@@ -17,6 +17,10 @@ import org.tensorflow.op.core.Squeeze
  *
  * Downsamples the input by taking maximum value over a temporal window of size [poolSize].
  *
+ * __Input shape:__  3D tensor with shape `(batch_size, steps, features)`.
+ *
+ * __Output shape:__ 3D tensor with shape `(batch_size, downsampled_steps, features)`.
+ *
  * @property [poolSize] Size of the temporal pooling window for each dimension of input.
  * @property [strides] The amount of shift for pooling window per each input dimension in each pooling step.
  * @property [padding] Padding strategy; can be either of [ConvPadding.VALID] which means no padding, or