scratchai - GitLite

KO | EN

gitlite — search

#hacktoberfest #typescript #llm #go #android #deep-learning #linux #docker #macos #nodejs #java #cli #awesome-list #mcp

scratchai

(★ 97)

scratchai is a Deep Learning library that aims to store all Deep Learning algorithms. With easy calls to do all the common tasks in AI.

File Explorer

Download Latest Version (.zip)

- config.yml
- FUNDING.yml
- - __init__.py
  - README.md
  - utils.py
- - __init__.py
  - color_code.py
  - DataLoader.py
  - DatasetLoader.py
  - ImageLoader.py
  - SegLoader.py
- - __init__.py
  - labels.py
  - README.md
- - __init__.py
  - clflearner.py
  - learner.py
  - metrics.py
  - quicktrain.py
- - __init__.py
  - common.py
  - utils.py
- - __init__.py
  - README.md
  - urls.py
- __init__.py
- _config.py
- imgutils.py
- init.py
- one_call.py
- utils.py
- __init__.py
- test_attacks.py
- test_learners.py
- test_loaders.py
- test_metrics.py
- test_nets.py
- test_one_calls.py
- test_utils.py
- README.md
.gitignore
CONTRIBUTING.md
LICENSE
README.md
requirements.txt
setup.py

# Installation Guide

1. Get the code

git clone https://github.com/iArunava/scratchai

Downloads the entire project code from GitHub to your computer.

cd scratchai

Moves into the project folder you just downloaded.

2. Python

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

pip install -r requirements.txt

Installs the Python libraries listed in requirements.txt (or similar).

python <실행할 파일명>.py # README에서 정확한 실행 파일명을 확인하세요

Runs the Python script (or module).

✅ If it runs without errors and prints output in the terminal, it worked.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# scratchai

## Builds

[![CircleCI](https://circleci.com/gh/iArunava/scratchai.svg?style=svg)](https://circleci.com/gh/iArunava/scratchai)

## Documentation

Table of Contents:

1. Classification

| Model | Paper | Implementation | Configurations |
| :--- | :-----: | :--: | :--: |
| Lenet | http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf | [Implementation](https://github.com/iArunava/scratchai/blob/master/scratchai/nets/clf/lenet.py) | |
| Alexnet | https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf | [Implementation](https://github.com/iArunava/scratchai/blob/master/scratchai/nets/clf/alexnet.py) | |
| VGG | https://arxiv.org/pdf/1409.1556.pdf | [Implementation](https://github.com/iArunava/scratchai/blob/master/scratchai/nets/clf/vgg.py) | VGG11, VGG11_BN, VGG13, VGG13_BN, VGG16_BN, VGG19, VGG19_BN, VGG_Dilated (For all the normal configurations) |
| Resnet | https://arxiv.org/abs/1512.03385 | [Implementation](https://github.com/iArunava/scratchai/blob/master/scratchai/nets/clf/resnet.py#L117) | Resnet18, Resnet34, Resnet50, Resnet101, Resnet150, Resnet_dilated (For all the previous resnets) |
| GoogLeNet | https://www.cs.unc.edu/~wliu/papers/GoogLeNet.pdf | [Implementation](https://github.com/iArunava/scratchai/blob/master/scratchai/nets/clf/googlenet.py) | |
| Resnext | https://arxiv.org/abs/1611.05431 | NA | |

2. Segmentation

| Model | Paper | Implementation |
| :--- | :-----: | :--: |
| UNet | https://arxiv.org/abs/1505.04597 | [Implementation](https://github.com/iArunava/scratchai/blob/master/scratchai/nets/seg/unet.py#L38) [Not checked] |
| ENet | https://arxiv.org/abs/1606.02147 | [Implementation](https://github.com/iArunava/scratchai/blob/master/scratchai/nets/seg/enet.py#L155) [Not checked] |

3. Generative Adversarial Networks

| Model | Paper | Implementation |
| :--- | :-----: | :--: |
| DCGAN | https://arxiv.org/abs/1511.06434 | NA |
| CycleGAN | https://arxiv.org/abs/1703.10593 | [Implementation](https://github.com/iArunava/scratchai/blob/master/scratchai/nets/gans/cycle_gan.py) [Not checked] |

4. Style Transfer

| Model | Paper | Implementation |
| :--- | :-----: | :--: |
| Image Transformation Network Justin et al. | [Perceptual Losses Paper](https://cs.stanford.edu/people/jcjohns/papers/eccv16/JohnsonECCV16.pdf)<br/>[Supplementary Material](https://cs.stanford.edu/people/jcjohns/papers/eccv16/JohnsonECCV16Supplementary.pdf) | [Implementation](https://github.com/iArunava/scratchai/blob/86d5011394592bde57eda40ba4682c8f26863b13/scratchai/nets/style_transfer/image_transformation_net.py#L75)

5. Attacks

| Attacks | Paper | Implementation |
| :--- | :-----: | :--: |
| Noise | NA | [Implementation](https://github.com/iArunava/scratchai/blob/master/scratchai/attacks/attacks/noise.py) |
| Semantic | https://arxiv.org/abs/1703.06857 | [Implementation](https://github.com/iArunava/scratchai/blob/master/scratchai/attacks/attacks/semantic.py)
| Saliency Map Method | https://arxiv.org/pdf/1511.07528.pdf | [Ongoing](https://github.com/iArunava/scratchai/blob/master/scratchai/attacks/attacks/saliency_map_method.py) |
| Fast Gradient Method | https://arxiv.org/abs/1412.6572 | [Implementation](https://github.com/iArunava/scratchai/blob/master/scratchai/attacks/attacks/fast_gradient_method.py) |
|Projected Gradient Descent | https://arxiv.org/pdf/1607.02533.pdf <br/> https://arxiv.org/pdf/1706.06083.pdf | [Implementation](https://github.com/iArunava/scratchai/blob/master/scratchai/attacks/attacks/fast_gradient_method.py) |
|DeepFool | https://arxiv.org/abs/1511.04599 [pdf](https://arxiv.org/pdf/1511.04599.pdf) | [Implementation](https://github.com/iArunava/scratchai/blob/master/scratchai/attacks/attacks/deepfool.py) |
  
  
## Tutorials

Tutorials on how to get the most out of scratchai can be found here: https://github.com/iArunava/scratchai/tree/master/tutorials

These are ongoing list of tutorials and scratchai is looking for more and more contributions. If you are willing to contribute 
please take a look at the `CONTRIBUTING.md` / open a issue.

## License
The code under this repository is distributed under MIT License. Feel free to use it in your own work with proper citations to this repository.