diff options
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala | 46 | ||||
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala | 34 |
2 files changed, 40 insertions, 40 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala b/mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala index a5b84116e6..913479f020 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala @@ -88,7 +88,7 @@ private[ann] trait LayerModel extends Serializable { * LayerModel implementation and the stack (batch) size * Developer is responsible for checking the size of output * when writing to it - * + * * @param data data * @param output output (modified in place) */ @@ -100,8 +100,8 @@ private[ann] trait LayerModel extends Serializable { * LayerModel implementation and the stack (batch) size * Developer is responsible for checking the size of * prevDelta when writing to it - * - * @param delta delta of this layer + * + * @param delta delta of this layer * @param output output of this layer * @param prevDelta the previous delta (modified in place) */ @@ -185,7 +185,7 @@ private[ann] object AffineLayerModel { /** * Creates a model of Affine layer - * + * * @param layer layer properties * @param weights vector for weights initialization * @param random random number generator @@ -202,8 +202,8 @@ private[ann] object AffineLayerModel { * where a is chosen in a such way that the weight variance corresponds * to the points to the maximal curvature of the activation function * (which is approximately 2.38 for a standard sigmoid) - * - * @param numIn number of inputs + * + * @param numIn number of inputs * @param numOut number of outputs * @param weights vector for weights initialization * @param random random number generator @@ -354,7 +354,7 @@ private[ann] trait TopologyModel extends Serializable { val layerModels: Array[LayerModel] /** * Forward propagation - * + * * @param data input data * @return array of outputs for each of the layers */ @@ -362,7 +362,7 @@ private[ann] trait TopologyModel extends Serializable { /** * Prediction of the model - * + * * @param data input data * @return prediction */ @@ -370,7 +370,7 @@ private[ann] trait TopologyModel extends Serializable { /** * Computes gradient for the network - * + * * @param data input data * @param target target output * @param cumGradient cumulative gradient @@ -384,7 +384,7 @@ private[ann] trait TopologyModel extends Serializable { /** * Feed forward ANN * - * @param layers + * @param layers Array of layers */ private[ann] class FeedForwardTopology private(val layers: Array[Layer]) extends Topology { override def model(weights: Vector): TopologyModel = FeedForwardModel(this, weights) @@ -398,7 +398,7 @@ private[ann] class FeedForwardTopology private(val layers: Array[Layer]) extends private[ml] object FeedForwardTopology { /** * Creates a feed forward topology from the array of layers - * + * * @param layers array of layers * @return feed forward topology */ @@ -408,7 +408,7 @@ private[ml] object FeedForwardTopology { /** * Creates a multi-layer perceptron - * + * * @param layerSizes sizes of layers including input and output size * @param softmaxOnTop wether to use SoftMax or Sigmoid function for an output layer. * Softmax is default @@ -534,7 +534,7 @@ private[ann] object FeedForwardModel { /** * Creates a model from a topology and weights - * + * * @param topology topology * @param weights weights * @return model @@ -546,7 +546,7 @@ private[ann] object FeedForwardModel { /** * Creates a model given a topology and seed - * + * * @param topology topology * @param seed seed for generating the weights * @return model @@ -610,7 +610,7 @@ private[ann] class DataStacker(stackSize: Int, inputSize: Int, outputSize: Int) /** * Stacks the data - * + * * @param data RDD of vector pairs * @return RDD of double (always zero) and vector that contains the stacked vectors */ @@ -643,7 +643,7 @@ private[ann] class DataStacker(stackSize: Int, inputSize: Int, outputSize: Int) /** * Unstack the stacked vectors into matrices for batch operations - * + * * @param data stacked vector * @return pair of matrices holding input and output data and the real stack size */ @@ -714,7 +714,7 @@ private[ml] class FeedForwardTrainer( /** * Sets weights - * + * * @param value weights * @return trainer */ @@ -725,7 +725,7 @@ private[ml] class FeedForwardTrainer( /** * Sets the stack size - * + * * @param value stack size * @return trainer */ @@ -737,7 +737,7 @@ private[ml] class FeedForwardTrainer( /** * Sets the SGD optimizer - * + * * @return SGD optimizer */ def SGDOptimizer: GradientDescent = { @@ -748,7 +748,7 @@ private[ml] class FeedForwardTrainer( /** * Sets the LBFGS optimizer - * + * * @return LBGS optimizer */ def LBFGSOptimizer: LBFGS = { @@ -759,7 +759,7 @@ private[ml] class FeedForwardTrainer( /** * Sets the updater - * + * * @param value updater * @return trainer */ @@ -771,7 +771,7 @@ private[ml] class FeedForwardTrainer( /** * Sets the gradient - * + * * @param value gradient * @return trainer */ @@ -801,7 +801,7 @@ private[ml] class FeedForwardTrainer( /** * Trains the ANN - * + * * @param data RDD of input and output vector pairs * @return model */ diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala index 9ff5252e4f..456e22de91 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala @@ -37,8 +37,8 @@ private[ml] trait MultilayerPerceptronParams extends PredictorParams /** * Layer sizes including input size and output size. * Default: Array(1, 1) - * - * @group param + * + * @group param */ final val layers: IntArrayParam = new IntArrayParam(this, "layers", "Sizes of layers from input layer to output layer" + @@ -56,8 +56,8 @@ private[ml] trait MultilayerPerceptronParams extends PredictorParams * a partition then it is adjusted to the size of this data. * Recommended size is between 10 and 1000. * Default: 128 - * - * @group expertParam + * + * @group expertParam */ final val blockSize: IntParam = new IntParam(this, "blockSize", "Block size for stacking input data in matrices. Data is stacked within partitions." + @@ -71,7 +71,7 @@ private[ml] trait MultilayerPerceptronParams extends PredictorParams /** * Allows setting the solver: minibatch gradient descent (gd) or l-bfgs. * l-bfgs is the default one. - * + * * @group expertParam */ final val solver: Param[String] = new Param[String](this, "solver", @@ -84,8 +84,8 @@ private[ml] trait MultilayerPerceptronParams extends PredictorParams /** * Model weights. Can be returned either after training or after explicit setting - * - * @group expertParam + * + * @group expertParam */ final val weights: Param[Vector] = new Param[Vector](this, "weights", " Sets the weights of the model ") @@ -156,8 +156,8 @@ class MultilayerPerceptronClassifier @Since("1.5.0") ( /** * Set the maximum number of iterations. * Default is 100. - * - * @group setParam + * + * @group setParam */ @Since("1.5.0") def setMaxIter(value: Int): this.type = set(maxIter, value) @@ -166,24 +166,24 @@ class MultilayerPerceptronClassifier @Since("1.5.0") ( * Set the convergence tolerance of iterations. * Smaller value will lead to higher accuracy with the cost of more iterations. * Default is 1E-4. - * - * @group setParam + * + * @group setParam */ @Since("1.5.0") def setTol(value: Double): this.type = set(tol, value) /** * Set the seed for weights initialization if weights are not set - * - * @group setParam + * + * @group setParam */ @Since("1.5.0") def setSeed(value: Long): this.type = set(seed, value) /** * Sets the model weights. - * - * @group expertParam + * + * @group expertParam */ @Since("2.0.0") def setWeights(value: Vector): this.type = set(weights, value) @@ -232,8 +232,8 @@ object MultilayerPerceptronClassifier * :: Experimental :: * Classification model based on the Multilayer Perceptron. * Each layer has sigmoid activation function, output layer has softmax. - * - * @param uid uid + * + * @param uid uid * @param layers array of layer sizes including input and output layers * @param weights vector of initial weights for the model that consists of the weights of layers * @return prediction model |