On Anytime Learning At Macroscale

Learning from sequential data dumps

(key) Requirements

Python 3.7
Pytorch 1.9.0
Hydra 1.1.0 (pip install hydra-core & pip install hydra-submitit-launcher)

Structure

├── crlapi           
  ├── benchmark.py    # Creates the data stream, feeds it to the model and evaluates it
  ├── core.py         # Abstract classes for 
  ├── logger.py   
  ├── sl
    ├── architectures
      ├── ...         # NN architectures used in this project
    ├── clmodels
      ├── ...         # Models (e.g. Single, gEns, ..., )
    ├── streams
      ├── ...         # CIFAR and MNIST stream implementatins

Running Experiments

To run experiments, you need to call the dataset specific run file, and you need to pass the configuration of the run. We have place the configurations in the previous directory (../configs). The config structure is as follows

    ├── configs
        ├── mnist
           ├── run.py                 # run file
           ├── test_usage_gmoe.yaml   # This is the "gMoE" model
           ├── test_finetune_mlp.yaml # This is the "Single Model"
           ... 
        ├── cifar
           ├── run.py                 # run file
           ├── test_finetune_vgg.yaml # This is the "Single Model"
           ├── test_usage_gmoe.yaml   # This is the "gMoE" model
           ...

To run an e.g. mnist gMoE run, the command is (launched from the directory just above (so cd ..)

PYTHONPATH=./ python configs/mnist/run.py -cn test_usage_gmoe n_megabatches=2 replay=1 clmodel.max_epochs=200

Important arguments

n_megabatches : controls the number of megabatches. So n_megabatches=1 is your regular full dataset training
replay : whether to use replay or not
clmodel.init_from_scratch : whether to reinitialize the model at every MB. Should only be used when replay=1
device : use cuda or cpu depending on your hardware

License

alma is released under the MIT license. See LICENSE for additional details about it. See also our Terms of Use and Privacy Policy.

Anytime Learning At Macroscale

Related tags

Overview

On Anytime Learning At Macroscale

(key) Requirements

Structure

Running Experiments

Important arguments

License

Owner

Meta Research

This is the material used in my free Persian course: Machine Learning with Python

Probabilistic time series modeling in Python

A model to predict steering torque fully end-to-end

Built on python (Mathematical straight fit line coordinates error predictor machine learning foundational model)

JMP is a Mixed Precision library for JAX.

Built various Machine Learning algorithms (Logistic Regression, Random Forest, KNN, Gradient Boosting and XGBoost. etc)

Machine learning that just works, for effortless production applications

This project impelemented for midterm of the Machine Learning #Zoomcamp #Alexey Grigorev

Predict the demand for electricity (R) - FRENCH

Flightfare-Prediction - It is a Flightfare Prediction Web Application Using Machine learning,Python and flask

scikit-learn models hyperparameters tuning and feature selection, using evolutionary algorithms.

Python Machine Learning Jupyter Notebooks (ML website)

Fundamentals of Machine Learning

Tutorials, examples, collections, and everything else that falls into the categories: pattern classification, machine learning, and data mining

Sleep stages are classified with the help of ML. We have used 4 different ML algorithms (SVM, KNN, RF, NN) to demonstrate them

A toolkit for making real world machine learning and data analysis applications in C++

AtsPy: Automated Time Series Models in Python (by @firmai)

The Simpsons and Machine Learning: What makes an Episode Great?

A library of sklearn compatible categorical variable encoders

PySurvival is an open source python package for Survival Analysis modeling