opringle / Gluonrank
Licence: other
Ranking made easy
Stars: ✭ 39
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Gluonrank
Efficientnet
Gluon implementation of EfficientNet and EfficientNet-lite
Stars: ✭ 30 (-23.08%)
Mutual labels: mxnet, gluon
baidu-salers-logo-prediction
baidu contest, url: http://dianshi.baidu.com/gemstone/competitions/detail?raceId=17
Stars: ✭ 16 (-58.97%)
Mutual labels: mxnet, gluon
gluon2pytorch
Gluon to PyTorch deep neural network model converter
Stars: ✭ 72 (+84.62%)
Mutual labels: mxnet, gluon
Mxnet Centernet
Gluon implementation of "Objects as Points", aka "CenterNet"
Stars: ✭ 29 (-25.64%)
Mutual labels: mxnet, gluon
OpSummary.MXNet
A tool to count operators and parameters of your MXNet-Gluon model.
Stars: ✭ 19 (-51.28%)
Mutual labels: mxnet, gluon
MXNet-EfficientNet
A Gluon Implement of EfficientNet
Stars: ✭ 12 (-69.23%)
Mutual labels: mxnet, gluon
CycleGAN-gluon-mxnet
this repo attemps to reproduce Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks(CycleGAN) use gluon reimplementation
Stars: ✭ 31 (-20.51%)
Mutual labels: mxnet, gluon
Autogluon
AutoGluon: AutoML for Text, Image, and Tabular Data
Stars: ✭ 3,920 (+9951.28%)
Mutual labels: mxnet, gluon
Gluon Face
An unofficial Gluon FR Toolkit for face recognition. https://gluon-face.readthedocs.io
Stars: ✭ 264 (+576.92%)
Mutual labels: mxnet, gluon
Aws Machine Learning University Accelerated Tab
Machine Learning University: Accelerated Tabular Data Class
Stars: ✭ 718 (+1741.03%)
Mutual labels: mxnet, gluon
AAAI 2019 EXAM
Official implementation of "Explicit Interaction Model towards Text Classification"
Stars: ✭ 68 (+74.36%)
Mutual labels: mxnet, gluon
Dog-Breed-Identification-Gluon
Kaggle 120种狗分类,Gluon实现
Stars: ✭ 45 (+15.38%)
Mutual labels: mxnet, gluon
model-zoo-old
The ONNX Model Zoo is a collection of pre-trained models for state of the art models in deep learning, available in the ONNX format
Stars: ✭ 38 (-2.56%)
Mutual labels: mxnet, gluon
gluon-faster-rcnn
Faster R-CNN implementation with MXNet Gluon API
Stars: ✭ 31 (-20.51%)
Mutual labels: mxnet, gluon
ResidualAttentionNetwork
A Gluon implement of Residual Attention Network. Best acc on cifar10-97.78%.
Stars: ✭ 104 (+166.67%)
Mutual labels: mxnet, gluon
gpu accelerated forecasting modeltime gluonts
GPU-Accelerated Deep Learning for Time Series using Modeltime GluonTS (Learning Lab 53). Event sponsors: Saturn Cloud, NVIDIA, & Business Science.
Stars: ✭ 20 (-48.72%)
Mutual labels: mxnet, gluon
GluonRank: Your Choice of Deep Learning for Ranking
GluonRank is a toolkit that enables easy implementation of collaborative filtering models using neural networks, to help your prototyping of state of the art ranking systems.
Installation
Pip
Make sure you are using Python 3.6. You can install MXNet
and GluonRank
using pip:
pip install --index-url https://test.pypi.org/simple/ gluonrank
Uploading to pypi for testing
Build distribution
python setup.py sdist bdist_wheel
bash
Upload to pypi test index
twine upload --repository-url https://test.pypi.org/legacy/ dist/*
bash
Docs
Coming soon... (it might be a while actually...)
ToDo
- [ ] Categorical features
- [ ] Get running with multiple categorical features, maintain performance when reducing to a single one
- [ ] Gracefully handle missing continuous embedding or categorical variables & user/item biases
- [ ] Do not require user to index their embedding values for a single matrix
- [ ] Continuous features
- [ ] Get running with 1 continous feature, maintain performance when excluded
- [ ] Get running with several continuous features
- [ ] Increase the efficiency of the evaluation function
- [ ] Speed up negative sampling... Negative sampling without collisions results in 5X training time.
(answer)[https://stackoverflow.com/questions/53576915/sample-n-zeros-from-a-sparse-coo-matrix/53577344#53577344]
- [x] Match spotlight performance with implicit interaction model on movielense data
- [x] Build ranking function as network method
-
- [ ] Create hosted docs
Features
- [ ] Allow for sampling more than one negative per interaction
- [ ] Allow for feedback that can be in the form of 0, 1 or -1. (eg swiping data)
Ideas
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].