本文整理汇总了Java中org.deeplearning4j.nn.conf.layers.setup.ConvolutionLayerSetup类的典型用法代码示例。如果您正苦于以下问题：Java ConvolutionLayerSetup类的具体用法？Java ConvolutionLayerSetup怎么用？Java ConvolutionLayerSetup使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
ConvolutionLayerSetup类属于org.deeplearning4j.nn.conf.layers.setup包，在下文中一共展示了ConvolutionLayerSetup类的4个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: getConfiguration
import org.deeplearning4j.nn.conf.layers.setup.ConvolutionLayerSetup; //导入依赖的package包/类
@Override
protected MultiLayerConfiguration getConfiguration()
{
final ConvulationalNetParameters parameters = (ConvulationalNetParameters) this.parameters;
final MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder().seed(parameters.getSeed())
.iterations(parameters.getIterations())
.optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).list(2)
.layer(0,
new ConvolutionLayer.Builder(new int[] { 1, 1 }).nIn(parameters.getInputSize()).nOut(1000)
.activation("relu").weightInit(WeightInit.RELU).build())
.layer(1,
new OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).nOut(parameters.getOutputSize())
.weightInit(WeightInit.XAVIER).activation("softmax").build())
.backprop(true).pretrain(false);
new ConvolutionLayerSetup(builder, parameters.getRows(), parameters.getColumns(), parameters.getChannels());
return builder.build();
}
示例2: getConfiguration
import org.deeplearning4j.nn.conf.layers.setup.ConvolutionLayerSetup; //导入依赖的package包/类
@Override
protected MultiLayerConfiguration getConfiguration()
{
final ConvulationalNetParameters parameters = (ConvulationalNetParameters) this.parameters;
final MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder().seed(parameters.getSeed())
.iterations(parameters.getIterations())
.gradientNormalization(GradientNormalization.RenormalizeL2PerLayer)
.optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).list(3)
.layer(0,
new ConvolutionLayer.Builder(10, 10).stride(2, 2).nIn(parameters.getChannels()).nOut(6)
.weightInit(WeightInit.XAVIER).activation("relu").build())
.layer(1, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[] { 2, 2 }).build())
.layer(2, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD)
.nOut(parameters.getOutputSize()).weightInit(WeightInit.XAVIER).activation("softmax").build())
.backprop(true).pretrain(false);
new ConvolutionLayerSetup(builder, parameters.getRows(), parameters.getColumns(), parameters.getChannels());
return builder.build();
}
示例3: getConfiguration
import org.deeplearning4j.nn.conf.layers.setup.ConvolutionLayerSetup; //导入依赖的package包/类
public static MultiLayerConfiguration getConfiguration() {
final int numRows = 28;
final int numColumns = 28;
int nChannels = 1;
int outputNum = 10;
int batchSize = 100;
int iterations = 10;
int seed = 123;
MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder()
.seed(seed)
.batchSize(batchSize)
.iterations(iterations)
.constrainGradientToUnitNorm(true)
.optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT)
.list(3)
.layer(0, new ConvolutionLayer.Builder(10, 10)
.nIn(nChannels)
.nOut(6)
.weightInit(WeightInit.XAVIER)
.activation("relu")
.build())
.layer(1, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[]{2, 2})
.build())
.layer(2, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD)
.nIn(150)
.nOut(outputNum)
.weightInit(WeightInit.XAVIER)
.activation("softmax")
.build())
.backprop(true).pretrain(false);
new ConvolutionLayerSetup(builder, numRows, numColumns, nChannels);
MultiLayerConfiguration conf = builder.build();
return conf;
}
示例4: getConfiguration
import org.deeplearning4j.nn.conf.layers.setup.ConvolutionLayerSetup; //导入依赖的package包/类
public static MultiLayerConfiguration getConfiguration() {
final int numRows = 128;
final int numColumns = 128;
int nChannels = 1;
int outputNum = 5;
int batchSize = 10;
int iterations = 5;
int seed = 123;
MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder()
.seed(seed)
.batchSize(batchSize)
.iterations(iterations)
.constrainGradientToUnitNorm(true)
.optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT)
.list(9)
.layer(0, new ConvolutionLayer.Builder(128, 128)
.nIn(nChannels)
.nOut(8)
.weightInit(WeightInit.XAVIER)
.build())
.layer(1, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[]{2, 2})
.build())
.layer(2, new ConvolutionLayer.Builder(10, 10)
.nIn(nChannels)
.nOut(6)
.weightInit(WeightInit.XAVIER)
.build())
.layer(3, new ConvolutionLayer.Builder(10, 10)
.nIn(nChannels)
.nOut(6)
.weightInit(WeightInit.XAVIER)
.build())
.layer(4, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[]{2, 2})
.build())
.layer(5, new ConvolutionLayer.Builder(10, 10)
.nIn(nChannels)
.nOut(6)
.weightInit(WeightInit.XAVIER)
.build())
.layer(6, new ConvolutionLayer.Builder(10, 10)
.nIn(nChannels)
.nOut(6)
.weightInit(WeightInit.XAVIER)
.build())
.layer(7, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[]{2, 2})
.build())
.layer(8, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD)
.nIn(150)
.nOut(outputNum)
.weightInit(WeightInit.XAVIER)
.activation("softmax")
.build())
.backprop(true).pretrain(false);
new ConvolutionLayerSetup(builder, numRows, numColumns, nChannels);
MultiLayerConfiguration conf = builder.build();
return conf;
}