search

haeusser / learning_by_association

This repository contains code for the paper Learning by Association - A versatile semi-supervised training method for neural networks (CVPR 2017) and the follow-up work Associative Domain Adaptation (ICCV 2017).
https://vision.in.tum.de/members/haeusser
Apache License 2.0
151 stars 63 forks source link

Inquiry about experimental result #14

Closed sweetdream33 closed 6 years ago

sweetdream33 commented 6 years ago

Thank you for providing us with the code. I'm running the train.py corresponding Domain adaptation (SVHN->MNIST) I only modified hyper parameter (visit_weight, walker weight = 0.5, steps = 9000) Result of eval.py looks like : image Accuracy of selected architecture is 97.62%. This result is lower than 99.5% (errors(%) = 0.51, Result of paper - Table 5 ). What's the reason? Do I have to modify parameters ( visit weight, walker weight, learning rate, steps)?

The hyper parameter settings I have run are shown below. image

haeusser commented 6 years ago

Well if you change the hyper parameters, the results will also change.

Please see this issue for a discussion of the hyper parameters.

Cheers, Philip