Test on smallNORM with parameters specified in the paper have very bad result

[YifeiAI]

Thanks for posting the code!

I tried your code on smallNORM dataset with the parameter specified in the paper: A=64 B=8 C=D=16, routing iteration = 3, batch_size = 64 (set the number myself). But the result is very bad (cannot even converge). However in the paper the author said the accuracy should be 97.8%. I am wondering why it is so sensitive to how many capsules in A and also routing iterations?

And could the author post more testing result with different number of capsules/ routing iteration/ learning rate/ batch size etc.

Thank you very much!

[sanketloke]

Facing a similar issue. In the initial runs, the result was quite bad with the smallNORB. After trying multiple runs, I was able to get a decent accuracy. I got similar huge variance in validation accuracy for the training runs with MNIST. @www0wwwjs1 do you know what might cause this much variance?

[maomran]

Because the test script doesn't read the latest training parameters, it reads the whole models saved starting from the first iteration, hence the first training parameters will have a terrible accuracy, try using the latest training parameters only, the output should be stable.

[ashleylid]

Has anyone here had similar results to me on smallNORB? Images for output are in issue #30 This is just the training loop.

[ashleygritzman]

I also get very poor performance when using 3 iterations on smallNORB. The model failed to learn anything after almost 30k iterations. Any suggestions?

[peerdavid]

I'm not sure if the dataset is loaded correctly: The smallNorb dataset contains 24300 stereo images, but the model loads 24300*2 images with depth 1. I think this is wrong and possible this leads to the bad performance...