scratchai
scratchai copied to clipboard
Published
20 hours ago •
iArunava
iArunava
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.
scratchai
Builds
Documentation
Table of Contents:
- Classification
| Model | Paper | Implementation | Configurations |
|---|---|---|---|
| Lenet | http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf | Implementation | |
| Alexnet | https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf | Implementation | |
| VGG | https://arxiv.org/pdf/1409.1556.pdf | Implementation | 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 | Resnet18, Resnet34, Resnet50, Resnet101, Resnet150, Resnet_dilated (For all the previous resnets) |
| GoogLeNet | https://www.cs.unc.edu/~wliu/papers/GoogLeNet.pdf | Implementation | |
| Resnext | https://arxiv.org/abs/1611.05431 | NA |
- Segmentation
| Model | Paper | Implementation |
|---|---|---|
| UNet | https://arxiv.org/abs/1505.04597 | Implementation [Not checked] |
| ENet | https://arxiv.org/abs/1606.02147 | Implementation [Not checked] |
- Generative Adversarial Networks
| Model | Paper | Implementation |
|---|---|---|
| DCGAN | https://arxiv.org/abs/1511.06434 | NA |
| CycleGAN | https://arxiv.org/abs/1703.10593 | Implementation [Not checked] |
- Style Transfer
| Model | Paper | Implementation |
|---|---|---|
| Image Transformation Network Justin et al. | Perceptual Losses Paper Supplementary Material |
Implementation |
- Attacks
| Attacks | Paper | Implementation |
|---|---|---|
| Noise | NA | Implementation |
| Semantic | https://arxiv.org/abs/1703.06857 | Implementation |
| Saliency Map Method | https://arxiv.org/pdf/1511.07528.pdf | Ongoing |
| Fast Gradient Method | https://arxiv.org/abs/1412.6572 | Implementation |
| Projected Gradient Descent | https://arxiv.org/pdf/1607.02533.pdf https://arxiv.org/pdf/1706.06083.pdf |
Implementation |
| DeepFool | https://arxiv.org/abs/1511.04599 pdf | Implementation |
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.
iArunava