Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/tokusumi/metric_learning_keras
https://github.com/tokusumi/metric_learning_keras
keras metric-learning
Last synced: about 1 month ago
JSON representation
- Host: GitHub
- URL: https://github.com/tokusumi/metric_learning_keras
- Owner: tokusumi
- Created: 2019-08-22T23:56:23.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2020-02-17T16:07:44.000Z (almost 5 years ago)
- Last Synced: 2024-10-16T10:41:47.899Z (3 months ago)
- Topics: keras, metric-learning
- Language: Jupyter Notebook
- Size: 43 KB
- Stars: 3
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Siamese Network with L2softmaxloss
Implemented with Keras## Overview
This repository includes a comparison between L2-softmaxloss vs softmaxloss for metric learning.
I constructed Siamese network to calculate pointwise similarity between two images.See [notebook](https://github.com/tokusumi/metric_learning_keras/blob/master/metric_learning_keras/L2SoftmaxLoss/notebooks/compare_L2SoftmaxLoss.ipynb)
## Dataset
MNIST handwritten digit image dataset: http://yann.lecun.com/exdb/mnist/## Results
![PR curve](https://github.com/tokusumi/metric_learning_keras/blob/master/metric_learning_keras/L2SoftmaxLoss/notebooks/PR_curve_l2.png)## Refs
### L2-SoftmaxLoss (L2-constrained Softmax Loss)
> Y. Wen, K. Zhang, Z. Li, and Y. Qiao. A discrimina- tive feature learning approach for deep face recognition. In European Conference on Computer Vision, pages 499–515. Springer, 2016.