MI-Prometheus
v0.3.1

Notes

  • Installation
  • Updating the documentation
    • Guidelines & examples
    • Some quotes about Code Documentation
  • License

MI-Prometheus Primer

  • MI-Prometheus Explained
    • Core concepts
    • Architecture
    • Configuration Management
  • Problems Explained
  • Models Explained
  • Workers Explained
    • Trainers
    • Tester
    • Initialization:
    • Iterations over the batches of samples:
    • Terminal conditions:
  • Grid Workers Explained
  • Helpers Explained

Research

  • Research: Reproducible Experiments
  • VIGIL Workshop experiments
    • Training MAC & S-MAC on CLEVR & CoGenT
      • Testing the trained models on CLEVR / CoGenT-A / CoGenT-B
    • Finetuning the CoGenT-A & CLEVR trained models on CoGenT-B
      • Testing the finetuned models on CoGenT-A / CoGenT-B
    • Finetuning the CLEVR-trained models on CoGenT-A
      • Testing the finetuned models on CoGenT-A / CoGenT-B
    • Collecting the results

Tutorials

  • Basics: LeNet-5 on MNIST

Package Reference

  • miprometheus.utils
    • AppState
    • DataDict
    • ParamInterface
    • ParamRegistry
    • SamplerFactory
    • Split Indices
    • StatisticsCollector
    • StatisticsAggregator
    • TimePlot
    • Losses
      • Masked BCEWithLogitsLoss
      • Masked CrossEntropyLoss
    • Problems Utils
      • GenerateFeatureMaps
      • Language
  • miprometheus.problems
    • Problem
    • ProblemFactory
    • ImageTextToClass Problems
      • CLEVR
      • Sort-Of-CLEVR
      • ShapeColorQuery
    • ImageToClass Problems
      • CIFAR-10
      • MNIST
    • SequenceToSequence Problems
      • VQA Problems
        • COG
      • Algorithmic SequenceToSequence Problems
        • Dual Comparison
        • Dual Distraction
        • Dual Ignore
        • Manipulation Spatial
        • Manipulation Temporal
        • Recall
      • TextToText Problems
        • TranslationAnki
    • VideoToClass Problems
      • Sequential MNIST
  • miprometheus.models
    • Model
    • SequentialModel
    • ModelFactory
    • Visual Question Answering baselines
      • CNN + LSTM
      • Stacked Attention Networks
      • MAC
      • Simplified MAC
      • Relational Networks
    • Image Classification models
    • Controllers for MANNs models
    • Memory-Augmented Neural Network (MANN) models
      • DWM
      • DNC
      • NTM
      • Encoder-Solver models
    • Others Models
      • LSTM
      • ThalNet
  • miprometheus.workers
    • Worker
    • Trainer
    • OfflineTrainer
    • OnlineTrainer
    • Tester
  • miprometheus.grid_workers
    • GridWorker
    • GridTrainerCPU
    • GridTrainerGPU
    • GridTesterCPU
    • GridTesterGPU
    • GridAnalyzer
  • miprometheus.helpers
    • IndexSplitter
    • ProblemInitializer
MI-Prometheus
  • Docs »
  • MI Prometheus documentation
  • Edit on GitHub

MI Prometheus documentation¶

MI Prometheus is an open source Python library, built using PyTorch, that enables reproducible Machine Learning research.

Notes

  • Installation
  • Updating the documentation
  • License

MI-Prometheus Primer

  • MI-Prometheus Explained
  • Problems Explained
  • Models Explained
  • Workers Explained
  • Grid Workers Explained
  • Helpers Explained

Research

  • Research: Reproducible Experiments
  • VIGIL Workshop experiments

Tutorials

  • Basics: LeNet-5 on MNIST

Package Reference

  • miprometheus.utils
  • miprometheus.problems
  • miprometheus.models
  • miprometheus.workers
  • miprometheus.grid_workers
  • miprometheus.helpers

Indices and tables¶

  • Index
  • Module Index
  • Search Page
Next

© Copyright 2018, Tomasz Kornuta, Vincent Marois, Ryan L. McAvoy, Younes Bouhadjar, Alexis Asseman, Vincent Albouy, T.S. Jayram, Ahmet S. Ozcan Revision 0cfa852d.

Built with Sphinx using a theme provided by Read the Docs.