org.deeplearning4j.nn.conf.inputs.InvalidInputTypeException: Invalid input: MergeVertex cannot merge CNN activations of different width/heights:first [depth,width,height] = [50,3,199], input 1 = [50,3,198]

Searched on Google with the first line of a JAVA stack trace?

We can recommend more relevant solutions and speed up debugging when you paste your entire stack trace with the exception message. Try a sample exception.

Recommended solutions based on your search

Samebug tips

Do you know how to solve this issue? Write a tip to help other users and build your expert profile.

Solutions on the web

via GitHub by sid-sahani
, 1 year ago
Invalid input: MergeVertex cannot merge CNN activations of different width/heights:first [depth,width,height] = [50,3,199], input 1 = [50,3,198]
org.deeplearning4j.nn.conf.inputs.InvalidInputTypeException: Invalid input: MergeVertex cannot merge CNN activations of different width/heights:first [depth,width,height] = [50,3,199], input 1 = [50,3,198]
at org.deeplearning4j.nn.conf.graph.MergeVertex.getOutputType(MergeVertex.java:133)
at org.deeplearning4j.nn.conf.ComputationGraphConfiguration.addPreProcessors(ComputationGraphConfiguration.java:372)
at org.deeplearning4j.nn.conf.ComputationGraphConfiguration$GraphBuilder.build(ComputationGraphConfiguration.java:620)
at org.deeplearning4j.examples.convolution.LegalSifterCompGraphCNN.main(LegalSifterCompGraphCNN.java:80)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)

Users with the same issue

You are the first who have seen this exception. Write a tip to help other users and build your expert profile.

Write tip

Know the solutions? Share your knowledge to help other developers to debug faster.