org.nd4j.linalg.activations.impl.ActivationMish 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.nd4j.linalg.activations.impl;
import lombok.EqualsAndHashCode;
import lombok.Getter;
import lombok.val;
import org.nd4j.linalg.activations.BaseActivationFunction;
import org.nd4j.linalg.api.ndarray.INDArray;
import org.nd4j.linalg.api.ops.impl.transforms.strict.Mish;
import org.nd4j.linalg.api.ops.impl.transforms.strict.MishDerivative;
import org.nd4j.linalg.factory.Nd4j;
import org.nd4j.common.primitives.Pair;
/**
* https://arxiv.org/ftp/arxiv/papers/1908/1908.08681.pdf
*/
@EqualsAndHashCode(callSuper = false)
@Getter
public class ActivationMish extends BaseActivationFunction {
@Override
public INDArray getActivation(INDArray in, boolean training) {
Nd4j.getExecutioner().execAndReturn(new Mish(in));
return in;
}
@Override
public Pair backprop(INDArray in, INDArray epsilon) {
assertShape(in, epsilon);
val dLdZ = Nd4j.getExecutioner().exec(new MishDerivative(in, in));
dLdZ.muli(epsilon);
return new Pair<>(in, null);
}
@Override
public String toString() {
return "mish";
}
}