Closed gagb closed 7 years ago
Hi.
I found that the default hyperparameter (learning_rate
=0.001, momentum
=0.5) is too high for semi-supervised / unsupervised learning.
learning_rate
=0.001, momentum
=0.9
learning_rate
=0.001, momentum
=0.1
learning_rate
=0.0001, momentum
=0.1
learning_rate
=0.0001, momentum
=0.1, seed
=2
learning_rate
=0.0001, momentum
=0.1, seed
=3
learning_rate
=0.0001, momentum
=0.1, seed
=4
I fixed the code.
Thank you :smiley:
The unsupervised version now gets ~28.5% classification error. Thanks! I am closing this issue for now because the lower performance seems to be because of choice of hyper-parameters and not because of an implementation error.
Hey
For the semi-supervised version (100 labels), the current version gets around 85% accuracy. Which is different from the graph in the readme.
Here is the resultant semi-supervised/dim_reduction/results.csv result.txt
The performance of the unsupervised dimensionality reduction also seems to have decreased. Here's the visualization using the current version. The separation is worse than the visualization shown in readme. The error rate on the training data for this visualization is ~40%. The error rate reported in the original paper is ~13.5%.
Thanks!