https://github.com/dyslevium/learning-deep-learning

https://github.com/dyslevium/learning-deep-learning

Last synced: 3 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/dyslevium/learning-deep-learning
• Owner: DYSLEVIUM
• Created: 2021-08-15T19:17:11.000Z (almost 4 years ago)
• Default Branch: main
• Last Pushed: 2024-05-24T10:00:49.000Z (about 1 year ago)
• Last Synced: 2025-01-20T19:26:42.686Z (4 months ago)
• Language: Jupyter Notebook
• Size: 37.8 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Papers

## NEAT

1. Evolving Neural Networks through

Augmenting Topologies https://nn.cs.utexas.edu/downloads/papers/stanley.ec02.pdf

## Diffusion Models

1. Denoising Diffusion Probabilistic Models: https://arxiv.org/pdf/2006.11239

1. Diffusion Models Beat GANs on Image Synthesis: https://arxiv.org/pdf/2105.05233

## GANs

1. GAN: https://arxiv.org/pdf/1406.2661.pdf

1. DCGAN: https://arxiv.org/pdf/1511.06434.pdf

1. WGAN: https://arxiv.org/pdf/1701.07875.pdf

1. GP: https://arxiv.org/pdf/1910.06922.pdf

1. Pix2Pix: https://arxiv.org/pdf/1611.07004.pdf

1. CycleGAN: https://arxiv.org/pdf/1703.10593.pdf

1. ProGAN: https://arxiv.org/pdf/1710.10196v3.pdf

1. StyleGAN: https://arxiv.org/pdf/1812.04948.pdf

1. StyleGAN2: https://arxiv.org/pdf/1912.04958.pdf

1. StyleGAN3: https://arxiv.org/pdf/2201.13433.pdf

1. StyleGAN1.T: https://arxiv.org/pdf/2301.09515.pdf

1. GauGAN: https://arxiv.org/pdf/1903.07291.pdf

1. GigaGAN: https://arxiv.org/pdf/2303.05511.pdf

## Super Resolution

1. PULSE: https://arxiv.org/pdf/2003.03808.pdf

1. SRGAN: https://arxiv.org/pdf/1609.04802.pdf

1. ESRGAN: https://arxiv.org/pdf/1809.00219.pdf

## Image Segmentation

1. UNet: https://arxiv.org/pdf/1505.04597

1. Attention U-Net: https://arxiv.org/pdf/1804.03999.pdf

1. R2U-Net: https://arxiv.org/ftp/arxiv/papers/1802/1802.06955.pdf

## Image Recognition

1. ResNet: https://arxiv.org/pdf/1512.03385.pdf

1. VGG: https://arxiv.org/pdf/1409.1556.pdf

1. GoogleNet (InceptionV1): https://arxiv.org/pdf/1409.4842.pdf

1. LeNet: https://arxiv.org/pdf/1609.04112.pdf

1. AlexNet: https://proceedings.neurips.cc/paper_files/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf

1. EfficientNetV1: https://arxiv.org/pdf/1905.11946.pdf

1. MobileNet: https://arxiv.org/pdf/1704.04861.pdf

1. SENet: https://arxiv.org/pdf/1611.05431.pdf

1. ResNeXt: https://arxiv.org/pdf/1611.05431.pdf

1. YOLOv1 (You Only Look Once): https://arxiv.org/pdf/1506.02640.pdf

1. YOLOv2: https://arxiv.org/pdf/1612.08242.pdf

1. YOLOv3: https://arxiv.org/pdf/1804.02767.pdf

1. YOLOv5

1. YOLOv6

1. YOLOv7

1. YOLOv8

## Image Restoration

1. Bringing Old Photo Back to Life: https://arxiv.org/pdf/2004.09484.pdf

## Image Colorization

1. DeOldify: https://github.com/jantic/DeOldify

1. DFDNet: https://arxiv.org/pdf/2008.00418.pdf

## Blind Face Restoration

1. CodeFormer: https://arxiv.org/pdf/2206.11253.pdf

1. DFDNet: https://arxiv.org/pdf/2008.00418.pdf

1. GAN Prior Embedded Network for Blind Face Restoration in the Wild: https://arxiv.org/abs/2105.06070

1. Blind Face Restoration via Deep Multi-scale Component Dictionaries: https://arxiv.org/pdf/2008.00418.pdf

## AI Photogrammetry

1. Instant-NGP: https://nvlabs.github.io/instant-ngp/assets/mueller2022instant.pdf

1. NERF: https://arxiv.org/pdf/2003.08934.pdf

1. LERF: https://arxiv.org/abs/2303.09553

1. Instruct 3D-to-3D: https://arxiv.org/abs/2303.15780

1. HyperReel: https://arxiv.org/abs/2301.02238

1. ProlificDreamer: https://arxiv.org/abs/2305.16213

1. HiFA: https://arxiv.org/pdf/2305.18766.pdf

## Diffusion

1. ControlNet: https://arxiv.org/pdf/2302.05543.pdf

## Voice Cloning

1. TalkNet 2: https://arxiv.org/abs/2104.08189

2. Textless NLP: https://ai.meta.com/blog/textless-nlp-generating-expressive-speech-from-raw-audio/

## Models

1. BERT:

1. Diffusion:

1. Transformers:

1. Attention Is All You Need: https://arxiv.org/pdf/1706.03762.pdf

1. Whisper

1. Vision Transformers

1. DINO Regularization: https://arxiv.org/pdf/2104.14294.pdf

# Videos

##Transformers

1. https://www.youtube.com/playlist?list=PLDw5cZwIToCvXLVY2bSqt7F2gu8y-Rqje

1. https://www.youtube.com/watch?v=XowwKOAWYoQ

1. https://www.youtube.com/watch?v=XSSTuhyAmnI

1. https://www.youtube.com/watch?v=iDulhoQ2pro

1. https://www.youtube.com/watch?v=kWLed8o5M2Y

1. https://www.youtube.com/watch?v=bCz4OMemCcA

## CNN

1. https://www.youtube.com/watch?v=8iIdWHjleIs

1. https://www.youtube.com/watch?v=Lakz2MoHy6o&t=275s

## Neural Networks

1. https://www.youtube.com/watch?v=pauPCy_s0Ok&t=9s

1. https://www.youtube.com/watch?v=FBpPjjhJGhk

## Markov Chains

1. https://www.youtube.com/playlist?list=PLM8wYQRetTxBkdvBtz-gw8b9lcVkdXQKV

## Notes to self

1.  Use mixed-precision

1.  Save model and optimizer on each epoch

1.  Decay the learning rate

1.  Use label_smoothning

1.  Use l1, l2, dropout and early stopping

1.  Use decorator for no_grad()

1.  Probably use PyTorch Lightning