Pinned Repositories
algorithm-components
This library was designed for high performance pipeline of feature transform and model prediction as a consistent solution for both online and offline scenes.
kaggle-competition-solution-avito-duplicate-ads-detection
Kaggle Competition Solution for Avito Duplicate Ads Detection competition
multi-label-bert-classification
Multi-label Bert Classification with focal loss weighting, auto cross-label data synthesis, adding exclude loss part among specific labels, upsampling, robust mean over all positive or negative loss, generating very fast inference-time model, etc.
multinomial-factorization-machines
Multinomial Factorization Machines
preprocess_tabular_data
Auto inspect tabular data and transform data with PMML
rmisdk
做算法的同学常常需要将做好的算法包装成服务,接受业务端请求,返回计算结果。RMISDK的目标是简化算法服务的上线过程,提供快速、稳定、可扩展的长连接服务。
technical-skill-summary
My technical skill summary
tensorflow_highlevelapi_example
Tensorflow high level API example
tensorflow_serving_examples
MNIST Java Client of tensorflow serving example 'https://tensorflow.github.io/serving/serving_basic'
topwords
Implementation of paper: Deng K, Bol P K, Li K J, et al. On the unsupervised analysis of domain-specific Chinese texts[J]. Proceedings of the National Academy of Sciences, 2016: 201516510.
qf6101's Repositories
qf6101/topwords
Implementation of paper: Deng K, Bol P K, Li K J, et al. On the unsupervised analysis of domain-specific Chinese texts[J]. Proceedings of the National Academy of Sciences, 2016: 201516510.
qf6101/multinomial-factorization-machines
Multinomial Factorization Machines
qf6101/tensorflow_serving_examples
MNIST Java Client of tensorflow serving example 'https://tensorflow.github.io/serving/serving_basic'
qf6101/rmisdk
做算法的同学常常需要将做好的算法包装成服务,接受业务端请求,返回计算结果。RMISDK的目标是简化算法服务的上线过程,提供快速、稳定、可扩展的长连接服务。
qf6101/kaggle-competition-solution-avito-duplicate-ads-detection
Kaggle Competition Solution for Avito Duplicate Ads Detection competition
qf6101/tensorflow_highlevelapi_example
Tensorflow high level API example
qf6101/ace-lessons
Hard-earned Lessons on Automatic Chord Estimation
qf6101/angel
A Flexible and Powerful Parameter Server for large-scale machine learning
qf6101/chord-recognition
Projects developed during the Spring 2017 Computational Audio course at Boston University.
qf6101/ismir2017_chords
ISMIR 2017: structured training for large vocab chord recognition
qf6101/light-elephant-bird
lightly upgrade the versions of protobuf and thrift in elephant bird
qf6101/melodia_python_tutorial
qf6101/MIRDataManager
qf6101/pytorch_examples
qf6101/vowpalwabbit-prediction-swig-wrapper
C++11 implementation of linear model prediction of vowpal wabbit trained model with supports of swig wrap and vowpal wabbit feature hash.
qf6101/xgboost
Some modifications to xgboost for quickscorer's model loading.