Examples that use Collective Learning
This is a list of examples that we've implemented to show you how to use Collective Learning locally. See and example of the gRPC server for the next step towards decentralized Colearn.
Mnist
Uses the standard Mnist database of handwritten images
- mnist_keras.
Uses the
KerasLearnerhelper class. Discussed in more detail here. - mnist_pytorch.
Uses the
PytorchLearnerhelper class. Discussed in more detail here.
Fraud
The fraud dataset consists of information about credit card transactions.
The task is to predict whether transactions are fraudulent or not.
The data needs to be downloaded from Kaggle,
and the data directory passed in with the flag --data_dir.
- fraud_mli.
Uses the
MachineLearningInterfacedirectly and detects fraud in bank transactions. - fraud_keras.
Loads data from numpy arrays and uses
KerasLearner.
Cifar10
Uses the standard Cifar10 database of images
- cifar_keras.
Uses the
KerasLearnerhelper class. - cifar_pytorch.
Uses the
PytorchLearnerhelper class.
Xray
A binary classification task that requires predicting pneumonia from images of chest X-rays.
The data need to be downloaded from Kaggle,
and the data directory passed in with the flag --data_dir
- xray_keras.
Uses the
KerasLearnerhelper class. - xray_pytorch.
Uses the
PytorchLearnerhelper class.
Iris
Uses the standard Iris dataset. The aim of this task is to classify examples into one of three iris species based on measurements of the flower.
- iris_random_forest.
Uses the
MachineLearningInterfacedirectly and a random forest for classification.