Skip to content

Commit

Permalink
Update README
Browse files Browse the repository at this point in the history
  • Loading branch information
adambielski authored Mar 7, 2018
1 parent 00dd52d commit 95fad77
Showing 1 changed file with 3 additions and 2 deletions.
5 changes: 3 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@ Requires [pytorch](http://pytorch.org/) 0.3.1 with torchvision 0.2.0
- *TripletSelector* - abstract class defining objects generating triplets based on embeddings and ground truth class labels. Can be used with *OnlineTripletLoss*.
- *AllTripletSelector*, *HardestNegativeTripletSelector*, *RandomNegativeTripletSelector*, *SemihardNegativeTripletSelector* - TripletSelector implementations

# Examples
# Examples - MNIST

We'll train embeddings on MNIST dataset. Experiments were run in [jupyter notebook](Experiments_MNIST.ipynb).

Expand Down Expand Up @@ -146,7 +146,8 @@ Here's what we got with random hard negatives for each positive pair.

# FashionMNIST

Similar experiments were conducted for FashionMNIST dataset where advantages of online negative mining are more visible. The exact same network architecture with only 2-dimensional embeddings was used, which is probably not complex enough for learning good embeddings.
Similar experiments were conducted for FashionMNIST dataset where advantages of online negative mining are slightly more visible. The exact same network architecture with only 2-dimensional embeddings was used, which is probably not complex enough for learning good embeddings.
More complex datasets with higher number classses should benefit even more from online mining.

## Baseline - classification

Expand Down

0 comments on commit 95fad77

Please sign in to comment.