Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

#6284 Why comment out the full connection layer for VGG16 #6348

Merged
merged 9 commits into from Sep 22, 2018
Merged

#6284 Why comment out the full connection layer for VGG16 #6348

Changes from 4 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
52e26a4
#6284 Why comment out the full connection layer for VGG16
crazymxm Sep 3, 2018
2246e3a
Merge branch 'master' into master
crockpotveggies Sep 13, 2018
ab49d08
Merge branch 'master' into master
saudet Sep 14, 2018
7290565
fix compare error
crazymxm Sep 17, 2018
e0c008b
Merge branch 'master' into master
saudet Sep 17, 2018
c17b6c8
recovery metaData
crazymxm Sep 17, 2018
d49318b
Merge branch 'master' into master
saudet Sep 18, 2018
585db04
Merge branch 'master' into master
crockpotveggies Sep 20, 2018
464e7b1
Merge branch 'master' into master
crockpotveggies Sep 22, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
19 changes: 10 additions & 9 deletions deeplearning4j/deeplearning4j-zoo/src/main/java/org/deeplearning4j/zoo/model/VGG16.java
View file
Open in desktop
Expand Up @@ -27,6 +27,7 @@
import org.deeplearning4j.nn.conf.WorkspaceMode;
import org.deeplearning4j.nn.conf.inputs.InputType;
import org.deeplearning4j.nn.conf.layers.ConvolutionLayer;
import org.deeplearning4j.nn.conf.layers.DenseLayer;
import org.deeplearning4j.nn.conf.layers.OutputLayer;
import org.deeplearning4j.nn.conf.layers.SubsamplingLayer;
import org.deeplearning4j.nn.graph.ComputationGraph;
Expand Down Expand Up @@ -156,16 +157,16 @@ public ComputationGraphConfiguration conf() {
.layer(17, new SubsamplingLayer.Builder()
.poolingType(SubsamplingLayer.PoolingType.MAX).kernelSize(2, 2)
.stride(2, 2).build(), "16")
// .layer(18, new DenseLayer.Builder().nOut(4096).dropOut(0.5)
// .build())
// .layer(19, new DenseLayer.Builder().nOut(4096).dropOut(0.5)
// .build())
.layer(18, new OutputLayer.Builder(
.layer(18, new DenseLayer.Builder().nOut(4096).dropOut(0.5)
.build())
.layer(19, new DenseLayer.Builder().nOut(4096).dropOut(0.5)
.build())
.layer(20, new OutputLayer.Builder(
LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD).name("output")
.nOut(numClasses).activation(Activation.SOFTMAX) // radial basis function required
.build(), "17")
.setOutputs("18")

.build(), "19")
.setOutputs("20")
.backprop(true).pretrain(false)
.setInputTypes(InputType.convolutionalFlat(inputShape[2], inputShape[1], inputShape[0]))
.build();

Expand All @@ -181,7 +182,7 @@ public ComputationGraph init() {

@Override
public ModelMetaData metaData() {
return new ModelMetaData(new int[][] {inputShape}, 1, ZooType.CNN);
return null ;//new ModelMetaData(new int[][] {inputShape}, 1, ZooType.CNN);
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why is this returning null?

}

@Override
Expand Down