search

m4nuC / aifiddle-issues

Train, visualize and share deep neural net
http://aifiddle.io
33 stars 1 forks source link

MNIST Conv net doesn't converge #10

Open tim-impactia opened 5 years ago

tim-impactia commented 5 years ago

Hello,

Using AI fiddle to create fully connected nets and single layer conv nets converges OK, however none of my attempts to use 2-3 convolution layers seem to get much above 50% accuracy.

To get a reference point I re implemented in AI Fiddle the simple conv net here: https://github.com/keras-team/keras/blob/master/examples/mnist_cnn.py and also ran it in a colaboratory notebook. The notebook was at 92% accuracy after the first epoch. In AIFiddle I get to around 50% with 1 epoch and a batch size of 32. Moving to a batch size of 128 (as used by the code sample) sees this crashing down to 10%.

Do you have any idea what could cause this?

m4nuC commented 5 years ago

Hi Tim,

Apologies for the delay, i've missed the notification.

Did you by chance save your experiment in AIFIddle ? If so, could you share that link ?

I've made many of such architecture in AiFIddle and it should work fine.

Thanks

tim-impactia commented 5 years ago

Hi Emmanuel ,

Hello I saved it on the Cloud with the name "Hushed Hammer", can you see it?

Thank you for creating aifiddle by the way, it's fantastic for teaching basic principles and experimenting.

tim-impactia commented 5 years ago

In case this helps: during a session where I showed aifiddle to 3 other devs we recreated that exact network. For 2 of us the network converged (> 90% accuracy), for the other 2 it got stuck around 50%. We couldn't see any differences that would explain it (I remained one of those for whom the network was stuck at 50%).

m4nuC commented 5 years ago

Yes that one: https://editor.aifiddle.io/models/cloud/831bcf2c-76f6-43ba-97f1-26ff4ec2f1e2. Thanks for the added info I will investigate. I am cooking up a major release now so that should come with that

m4nuC commented 5 years ago

In case this helps: during a session where I showed aifiddle to 3 other devs we recreated that exact network. For 2 of us the network converged (> 90% accuracy), for the other 2 it got stuck around 50%. We couldn't see any differences that would explain it (I remained one of those for whom the network was stuck at 50%).

Would you by any chance have a link to those models ?