本文整理了Java中org.deeplearning4j.nn.api.Layer.type()
方法的一些代码示例,展示了Layer.type()
的具体用法。这些代码示例主要来源于Github
/Stackoverflow
/Maven
等平台,是从一些精选项目中提取出来的代码,具有较强的参考意义,能在一定程度帮忙到你。Layer.type()
方法的具体详情如下:
包路径:org.deeplearning4j.nn.api.Layer
类名称:Layer
方法名:type
[英]Returns the layer type
[中]返回图层类型
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
@Override
public Type type() {
return insideLayer.type();
}
代码示例来源:origin: org.deeplearning4j/deeplearning4j-ui_2.11
if (layer.type().equals(Layer.Type.CONVOLUTIONAL)) {
org.deeplearning4j.nn.conf.layers.ConvolutionLayer layer1 =
(org.deeplearning4j.nn.conf.layers.ConvolutionLayer) layer.conf().getLayer();
代码示例来源:origin: org.deeplearning4j/deeplearning4j-ui_2.10
if (layer.type().equals(Layer.Type.CONVOLUTIONAL)) {
org.deeplearning4j.nn.conf.layers.ConvolutionLayer layer1 =
(org.deeplearning4j.nn.conf.layers.ConvolutionLayer) layer.conf().getLayer();
代码示例来源:origin: org.deeplearning4j/deeplearning4j-ui_2.11
MultiLayerNetwork l = (MultiLayerNetwork) model;
for (Layer layer : l.getLayers()) {
if (!(layer instanceof FrozenLayer) && layer.type() == Layer.Type.CONVOLUTIONAL) {
INDArray output = layer.activate();
int sampleDim = output.shape()[0] == 1 ? 0 : rnd.nextInt(output.shape()[0] - 1) + 1;
ComputationGraph l = (ComputationGraph) model;
for (Layer layer : l.getLayers()) {
if (!(layer instanceof FrozenLayer) && layer.type() == Layer.Type.CONVOLUTIONAL) {
INDArray output = layer.activate();
int sampleDim = output.shape()[0] == 1 ? 0 : rnd.nextInt(output.shape()[0] - 1) + 1;
代码示例来源:origin: org.deeplearning4j/deeplearning4j-ui_2.10
MultiLayerNetwork l = (MultiLayerNetwork) model;
for (Layer layer : l.getLayers()) {
if (!(layer instanceof FrozenLayer) && layer.type() == Layer.Type.CONVOLUTIONAL) {
INDArray output = layer.activate();
int sampleDim = output.shape()[0] == 1 ? 0 : rnd.nextInt(output.shape()[0] - 1) + 1;
ComputationGraph l = (ComputationGraph) model;
for (Layer layer : l.getLayers()) {
if (!(layer instanceof FrozenLayer) && layer.type() == Layer.Type.CONVOLUTIONAL) {
INDArray output = layer.activate();
int sampleDim = output.shape()[0] == 1 ? 0 : rnd.nextInt(output.shape()[0] - 1) + 1;
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
break;
if (layer.type().equals(Layer.Type.CONVOLUTIONAL)) {
task.setArchitectureType(Task.ArchitectureType.CONVOLUTION);
break;
} else if (layer.type().equals(Layer.Type.RECURRENT)
|| layer.type().equals(Layer.Type.RECURSIVE)) {
task.setArchitectureType(Task.ArchitectureType.RECURRENT);
break;
break;
if (layer.type().equals(Layer.Type.CONVOLUTIONAL)) {
task.setArchitectureType(Task.ArchitectureType.CONVOLUTION);
break;
} else if (layer.type().equals(Layer.Type.RECURRENT)
|| layer.type().equals(Layer.Type.RECURSIVE)) {
task.setArchitectureType(Task.ArchitectureType.RECURRENT);
break;
代码示例来源:origin: neo4j-contrib/neo4j-ml-procedures
for (Layer layer : model.getLayers()) {
Node node = node("Layer",
"type", layer.type().name(), "index", layer.getIndex(),
"pretrainLayer", layer.isPretrainLayer(), "miniBatchSize", layer.getInputMiniBatchSize(),
"numParams", layer.numParams());
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
if (inputIs2d && input.rank() == 3 && layers[layers.length - 1].type() == Type.RECURRENT) {
内容来源于网络,如有侵权,请联系作者删除!