org.deeplearning4j.nn.conf.weightnoise.WeightNoise Maven / Gradle / Ivy
/*
* ******************************************************************************
* *
* *
* * This program and the accompanying materials are made available under the
* * terms of the Apache License, Version 2.0 which is available at
* * https://www.apache.org/licenses/LICENSE-2.0.
* *
* * See the NOTICE file distributed with this work for additional
* * information regarding copyright ownership.
* * Unless required by applicable law or agreed to in writing, software
* * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
* * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
* * License for the specific language governing permissions and limitations
* * under the License.
* *
* * SPDX-License-Identifier: Apache-2.0
* *****************************************************************************
*/
package org.deeplearning4j.nn.conf.weightnoise;
import lombok.Data;
import org.deeplearning4j.nn.api.Layer;
import org.deeplearning4j.nn.api.ParamInitializer;
import org.deeplearning4j.nn.conf.distribution.Distribution;
import org.deeplearning4j.nn.conf.distribution.Distributions;
import org.nd4j.linalg.api.ndarray.INDArray;
import org.nd4j.linalg.api.ops.impl.transforms.pairwise.arithmetic.AddOp;
import org.nd4j.linalg.api.ops.impl.transforms.pairwise.arithmetic.MulOp;
import org.nd4j.linalg.factory.Nd4j;
import org.deeplearning4j.nn.workspace.LayerWorkspaceMgr;
import org.deeplearning4j.nn.workspace.ArrayType;
import org.nd4j.shade.jackson.annotation.JsonProperty;
@Data
public class WeightNoise implements IWeightNoise {
private Distribution distribution;
private boolean applyToBias;
private boolean additive;
/**
* @param distribution Distribution for additive noise
*/
public WeightNoise(Distribution distribution) {
this(distribution, false, true);
}
/**
* @param distribution Distribution for noise
* @param additive If true: noise is added to weights. If false: noise is multiplied by weights
*/
public WeightNoise(Distribution distribution, boolean additive) {
this(distribution, false, additive);
}
/**
* @param distribution Distribution for noise
* @param applyToBias If true: apply to biases also. If false (default): apply only to weights
* @param additive If true: noise is added to weights. If false: noise is multiplied by weights
*/
public WeightNoise(@JsonProperty("distribution") Distribution distribution,
@JsonProperty("applyToBias") boolean applyToBias,
@JsonProperty("additive") boolean additive) {
this.distribution = distribution;
this.applyToBias = applyToBias;
this.additive = additive;
}
@Override
public INDArray getParameter(Layer layer, String paramKey, int iteration, int epoch, boolean train, LayerWorkspaceMgr workspaceMgr) {
ParamInitializer init = layer.conf().getLayer().initializer();
INDArray param = layer.getParam(paramKey);
if (train && init.isWeightParam(layer.conf().getLayer(), paramKey) ||
(applyToBias && init.isBiasParam(layer.conf().getLayer(), paramKey))) {
org.nd4j.linalg.api.rng.distribution.Distribution dist = Distributions.createDistribution(distribution);
INDArray noise = dist.sample(param.ulike());
INDArray out = workspaceMgr.createUninitialized(ArrayType.INPUT, param.dataType(), param.shape(), param.ordering());
if (additive) {
Nd4j.getExecutioner().exec(new AddOp(param, noise,out));
} else {
Nd4j.getExecutioner().exec(new MulOp(param, noise, out));
}
return out;
}
return param;
}
@Override
public WeightNoise clone() {
return new WeightNoise(distribution, applyToBias, additive);
}
}