paiutils


Namepaiutils JSON
Version 3.1.1 PyPI version JSON
download
home_pagehttps://github.com/Tiger767/PAI-Utils
SummaryAn artificial intelligence utilities package built to remove the delays of machine learning research.
upload_time2020-11-22 04:25:57
maintainer
docs_urlNone
authorTravis Hammond
requires_python>=3.7
license
keywords
VCS
bugtrack_url
requirements No requirements were recorded.
Travis-CI No Travis.
coveralls test coverage No coveralls.
            # PAI-Utils

Programming Artificial Intelligence Utilities is a package that aims to make
artificial intelligence and machine learning programming easier through
abstractions of extensive APIs, research paper implementations, and data
manipulation.

Modules in this package are used extensively in [this playlist](https://www.youtube.com/watch?v=4_oJMTfTBYY&list=PLZkmLNZl0Wkw9KSJMBhbalbsxmrjdlgv3).
The reinforcement modules are used [here](https://github.com/Tiger767/OpenAIGymResults).

Package Features
- Analytics
  - Plotting of data through embedding algorithms, such as Isomap and TSNE
- Audio
  - Recording and playing
  - Volume, speed, and pitch manipulation
  - Trimming and Splitting
  - Spectrogram, Fbanks, and MFCC creation
  - Audio file conversions
- Image
  - Simplified OpenCV Interface
- Autoencoder
  - Trainer and Predictor
  - Trainer with extra decoder
  - Basic network architecture creation
- Evolution Algorithm
  - One dimensional evolution algorithm
  - Hyperparameter tuner
- VAE
  - Trainer
- GAN
  - Trainer and Predictor
  - GANI Trainer (GAN which takes provided Inputs)
- Neural Network
  - Trainer and Predictor
  - Dense layers that combine batch norm
  - Convolution layers that combine batch norm, max pooling, upsampling, and transposing
- Reinforcement
  - OpenAI Gym wrapper
  - Multi-agent adverserial environment
  - Greedy, ascetic, and stochastic policies
  - Noise Policies
  - Exponential, linear, and constant decay
  - Ring and normal memory
  - Agents
    - QAgent: Q-learning with a table
    - DQNAgent Q-learning with a neural network model
    - PGAgent: State to action neural network model (Actor) trained with
               policy gradients
    - DDPGAgent: State to continous action space neural network model trained
                 with deterministic policy gradients (Not working yet)
- Reinforcement Agents
  - DQNPGAgent: A combination of a DQN and PG agent into one agent
  - A2CAgent: Advantage Actor Critic agent
  - PPOAgent: Proximal Policy Optimization agent
  - TD3Agent: Twin Delayed DDPG Agent (Not working yet)



            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/Tiger767/PAI-Utils",
    "name": "paiutils",
    "maintainer": "",
    "docs_url": null,
    "requires_python": ">=3.7",
    "maintainer_email": "",
    "keywords": "",
    "author": "Travis Hammond",
    "author_email": "",
    "download_url": "https://files.pythonhosted.org/packages/28/c8/8edd9962cd0051cd2a650f064437eaf027100060092e25b994a1caefabb5/paiutils-3.1.1.tar.gz",
    "platform": "",
    "description": "# PAI-Utils\n\nProgramming Artificial Intelligence Utilities is a package that aims to make\nartificial intelligence and machine learning programming easier through\nabstractions of extensive APIs, research paper implementations, and data\nmanipulation.\n\nModules in this package are used extensively in [this playlist](https://www.youtube.com/watch?v=4_oJMTfTBYY&list=PLZkmLNZl0Wkw9KSJMBhbalbsxmrjdlgv3).\nThe reinforcement modules are used [here](https://github.com/Tiger767/OpenAIGymResults).\n\nPackage Features\n- Analytics\n  - Plotting of data through embedding algorithms, such as Isomap and TSNE\n- Audio\n  - Recording and playing\n  - Volume, speed, and pitch manipulation\n  - Trimming and Splitting\n  - Spectrogram, Fbanks, and MFCC creation\n  - Audio file conversions\n- Image\n  - Simplified OpenCV Interface\n- Autoencoder\n  - Trainer and Predictor\n  - Trainer with extra decoder\n  - Basic network architecture creation\n- Evolution Algorithm\n  - One dimensional evolution algorithm\n  - Hyperparameter tuner\n- VAE\n  - Trainer\n- GAN\n  - Trainer and Predictor\n  - GANI Trainer (GAN which takes provided Inputs)\n- Neural Network\n  - Trainer and Predictor\n  - Dense layers that combine batch norm\n  - Convolution layers that combine batch norm, max pooling, upsampling, and transposing\n- Reinforcement\n  - OpenAI Gym wrapper\n  - Multi-agent adverserial environment\n  - Greedy, ascetic, and stochastic policies\n  - Noise Policies\n  - Exponential, linear, and constant decay\n  - Ring and normal memory\n  - Agents\n    - QAgent: Q-learning with a table\n    - DQNAgent Q-learning with a neural network model\n    - PGAgent: State to action neural network model (Actor) trained with\n               policy gradients\n    - DDPGAgent: State to continous action space neural network model trained\n                 with deterministic policy gradients (Not working yet)\n- Reinforcement Agents\n  - DQNPGAgent: A combination of a DQN and PG agent into one agent\n  - A2CAgent: Advantage Actor Critic agent\n  - PPOAgent: Proximal Policy Optimization agent\n  - TD3Agent: Twin Delayed DDPG Agent (Not working yet)\n\n\n",
    "bugtrack_url": null,
    "license": "",
    "summary": "An artificial intelligence utilities package built to remove the delays of machine learning research.",
    "version": "3.1.1",
    "split_keywords": [],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "749b77018693a8fc69e27f682dd9f11d",
                "sha256": "e07d1db3c4513c29abb124a14c6368381ef9312ec6ad05c8df62d4fab8e16770"
            },
            "downloads": -1,
            "filename": "paiutils-3.1.1-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "749b77018693a8fc69e27f682dd9f11d",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.7",
            "size": 2520128,
            "upload_time": "2020-11-22T04:25:55",
            "upload_time_iso_8601": "2020-11-22T04:25:55.721714Z",
            "url": "https://files.pythonhosted.org/packages/fc/fb/54312d6b84d381805c122aa25d3657403141540c088af4a2d001b98b98c0/paiutils-3.1.1-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "ac27af568516cecedcdb0a85ba0249c0",
                "sha256": "9faf7f4e5f8b14fcc8db0edf743250ea5aabc0c29800816ff54e685777560f8b"
            },
            "downloads": -1,
            "filename": "paiutils-3.1.1.tar.gz",
            "has_sig": false,
            "md5_digest": "ac27af568516cecedcdb0a85ba0249c0",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.7",
            "size": 2504124,
            "upload_time": "2020-11-22T04:25:57",
            "upload_time_iso_8601": "2020-11-22T04:25:57.414783Z",
            "url": "https://files.pythonhosted.org/packages/28/c8/8edd9962cd0051cd2a650f064437eaf027100060092e25b994a1caefabb5/paiutils-3.1.1.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2020-11-22 04:25:57",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "github_user": null,
    "github_project": "Tiger767",
    "error": "Could not fetch GitHub repository",
    "lcname": "paiutils"
}
        
Elapsed time: 0.17582s