Commit acb45d3a authored by MAIRAL Julien's avatar MAIRAL Julien

update

parent 50d7d045
......@@ -49,7 +49,7 @@ or [here](http://pascal.inrialpes.fr/data2/mairal/data/cifar10.mat) (for the raw
See also [here](https://www.cs.toronto.edu/~kriz/cifar.html) for the original dataset.
For the supervised variant, we feature a 14-layer architecture that achieves about 90.6% accuracy. For the unsupervised one, we provide a two-layer architecture. By changing the number of filters, the accuracy ranges from 77.2% accuracy (with 64 and 256 filters on the first and second layer respectively) to 86.2% (with 2048 and 32768 filters).
All of these results are for a single model with no data augmentation. With data augmentation, the supervised model achieves about 92%.
All of these results are for a single model with no data augmentation. With data augmentation (flips + basic crops), the supervised model achieves about 92%.
## Q: Why do the results seem to be slightly better than in the original paper?
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment