Git Product home page Git Product logo

eva5_ai_projects_new's Introduction

AI Projects framework

AI Project template structure

├── .vscode/
│   ├── launch.json
│   └── settings.json
├── analysis/
├── check_points/
│   └── Session7_assignment_vgg.h5
├── configs/
│   ├── basic_config.py
│   └── basic_config_Session6.py
├── data/
│   ├── base_data_utils.py
│   ├── data_loaders/
│   │   └── base_data_loader.py
│   ├── data_transforms/
│   │   └── base_data_transforms.py
│   └── datasets/
│       └── MNIST/
│           ├── processed/
│           │   ├── test.pt
│           │   └── training.pt
│           └── raw/
│               ├── t10k-images-idx3-ubyte
│               ├── t10k-images-idx3-ubyte.gz
│               ├── t10k-labels-idx1-ubyte
│               ├── t10k-labels-idx1-ubyte.gz
│               ├── train-images-idx3-ubyte
│               ├── train-images-idx3-ubyte.gz
│               ├── train-labels-idx1-ubyte
│               └── train-labels-idx1-ubyte.gz
├── dev.env
├── docs/
├── draw_project_dir_tree.py
├── LICENSE
├── logs/
│   └── project1_test.txt
├── main.py
├── models/
│   ├── activation_functions/
│   ├── base_network_utils.py
│   ├── evaluator.py
│   ├── learning_rates/
│   ├── losses/
│   ├── model_builder.py
│   ├── networks/
│   │   ├── cifar10_dialation_dsc.py
│   │   ├── cifar10_dialation_dsc_vgg.py
│   │   ├── custom_layers/
│   │   │   └── ghost_batch_norm.py
│   │   ├── mnist_ghost_bn_se.py
│   │   └── mnist_normal_bn_se.py
│   ├── optimizers/
│   └── trainer.py
├── orchestrators/
│   ├── __init__.py
│   ├── base_orchestrator.py
│   ├── session6_assignment .ipynb
│   ├── Session7_assignment_V2.ipynb
│   ├── Session7_assignment_V3.ipynb
│   └── Session7_assignment_vgg_final.ipynb
├── README.md
├── requirements.txt
├── setup.py
├── unit_tests/
└── utils/
    ├── logger_utils.py
    ├── misc_utils.py
    └── visualization_utils.py

How to start a new AI project using this framework?

Whenever we need to create a new deep learning project, you need to update/create following files.

  1. orchestrators/<orchestrator.py> - Orchestrator is the file which is ipynb file which interact with all other files in the project and make things done - Create/update required for specific project
  2. basic_config.py - This is a configuration file which has most of the configuration values needed for the entire project - Create/update required for specific project
  3. models/networks/<network_architecture>.py - This is the file where you need to define the DNN (ANN/CNN/RNN/LSTMs/GRUs/GANs) architecture - Create/update required for specific project
  4. models/networks/custom_layers/<custom_layer>.py - Customer layers are defined in this location. - Create/update required for specific project (optional)
  5. logs/<project_log.txt> - This is where logs of the project are stored.
  6. checkpoints/<project_model.h5> - This is where models can be saved.
  7. And other dir/file names in the above directory tree are self explanatory based on their file name

Deep Learning Framework used:

PyTorch

eva5_ai_projects_new's People

Contributors

nagapavan525 avatar ezhirko avatar

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.