It must be a very stupid question, but since I have not such sufficient know ledge storage and having no more time to search the answer of it, I have to put it here to ask for help. I generated a training dataset of images of simple geometric shapes as triangles, squares, diamonds etc. by programs and constructed a CNN with two convolutional layers and one pooling layer also a final fully connected layer to learn the classifications of these shapes. But the network just does not to learn it. I mean the loss just does not decrease. What is the cause?

  • 2
    $\begingroup$ It is very difficult to debug your issue without having a look at the code. Moreover, I think you should ask this question on Stack Overflow and provide them the code too and try to be more specific. $\endgroup$ – nbro Apr 8 '19 at 16:09
  • $\begingroup$ I used Caffe to do this work. The only code I wrote is a solver.prototxt and a prototxt file of the network. $\endgroup$ – piratesailor Apr 9 '19 at 2:10
  • $\begingroup$ @nbro not SO, datascience.SE $\endgroup$ – DuttaA Apr 11 '19 at 12:45
  • 1
    $\begingroup$ @DuttaA SO is also ok. SO is a website for general programming issues and there are a lot of tags related to ML/AI. $\endgroup$ – nbro Apr 11 '19 at 12:53

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.