Giter VIP home page Giter VIP logo

pyrameter's People

Contributors

btovar avatar craymichael avatar jeffkinnison avatar rileygriffith avatar sabraha2 avatar

Stargazers

avatar avatar avatar

Watchers

avatar avatar

Forkers

applejax124 prijatelj rileygriffith craymichael gayan225 sabraha2 vishalbelsare btovar

pyrameter's Issues

Neural Architecture Search

Implement NAS as a search method, incorporating reinforcement learning a la DeepMind. This will totally go well.

Evolutionary Algorithms/Population-Based Methods

This project needs support for evolutionary algs and other population-based methods. Essentially, instead of generating single hyperparameter sets at a time, there should be a way to generate a batch of them.

This could be implemented using a generator in SearchSpace.generate() with n samples and updating when the generator is empty.

KeyError: 'domain_kwargs' when loading results file

When attempting to load and plot with the results file, get the following KeyError

File "driver_mnist.py", line 67, in <module>
    opt.load()
  File "/afs/crc.nd.edu/user/s/sabraha2/Projects/optimization/Neural_network_search/venv/lib/python3.7/site-packages/shadho/shadho.py", line 219, in load
    super().load()
  File "/afs/crc.nd.edu/user/s/sabraha2/Projects/optimization/Neural_network_search/venv/lib/python3.7/site-packages/pyrameter/optimizer.py", line 174, in load
    self.searchspaces = self.backend.load()
  File "/afs/crc.nd.edu/user/s/sabraha2/Projects/optimization/Neural_network_search/venv/lib/python3.7/site-packages/pyrameter/backend/local.py", line 46, in load
    return [SearchSpace.from_json(obj) for obj in objs]
  File "/afs/crc.nd.edu/user/s/sabraha2/Projects/optimization/Neural_network_search/venv/lib/python3.7/site-packages/pyrameter/backend/local.py", line 46, in <listcomp>
    return [SearchSpace.from_json(obj) for obj in objs]
  File "/afs/crc.nd.edu/user/s/sabraha2/Projects/optimization/Neural_network_search/venv/lib/python3.7/site-packages/pyrameter/searchspace.py", line 132, in from_json
    domains = [Domain.from_json(d) for d in obj['domains']]
  File "/afs/crc.nd.edu/user/s/sabraha2/Projects/optimization/Neural_network_search/venv/lib/python3.7/site-packages/pyrameter/searchspace.py", line 132, in <listcomp>
    domains = [Domain.from_json(d) for d in obj['domains']]
  File "/afs/crc.nd.edu/user/s/sabraha2/Projects/optimization/Neural_network_search/venv/lib/python3.7/site-packages/pyrameter/domains/base.py", line 112, in from_json
    return cls.from_json(obj)
  File "/afs/crc.nd.edu/user/s/sabraha2/Projects/optimization/Neural_network_search/venv/lib/python3.7/site-packages/pyrameter/domains/discrete.py", line 73, in from_json
    rng = obj['domain_kwargs']['random_state']
KeyError: 'domain_kwargs'

Finish Database Backend Support

At present, database support for storing search data is incomplete, working only with JSON. The full suite should support Mongo and SQLite (at the very least).

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.