s-chh

PyTorch-Scratch-Vision-Transformer-ViT. Simple and easy to understand PyTorch implementation of Vision Transformer (ViT) from scratch, with detailed steps. Tested on common datasets like MNIST, CIFAR10, and more.

2D-Positional-Encoding-Vision-Transformer. PyTorch implementation of 2D Positional Encodings for Vision Transformers (ViT). Positional Encodings/Embeddings: Sinusoidal (Absolute), Learnable, Relative and Rotation (Rope).

PyTorch-GANs. From scratch, simple and easy-to-understand Pytorch implementation of various generative adversarial network (GAN): GAN, DCGAN, Conditional GAN (cGAN), WGAN, WGAN-GP, CycleGAN, LSGAN, and StarGAN.

Find-Duplicate-Photos-Video. Python code to find duplicate images (photos) and videos in folders recursively and delete them (Optional).

PyTorch-Scratch-LLM. Simple and easy to understand PyTorch implementation of Large Language Model (LLM) GPT and LLAMA from scratch with detailed steps. Implemented: Byte-Pair Tokenizer, Rotational Positional Embedding (RoPe), SwishGLU, RMSNorm, Mixture of Experts (MOE). Tested on Taylor Swift song lyrics dataset.

PatchSwap. Official Pytorch code for PatchSwap: A Regularization Technique for Vision Transformers

PyTorch-DANN. Unofficial PyTorch implementation of Domain-Adversarial Training of Neural Networks

PatchRot. Official Pytorch Implementation of PatchRot: PatchRot: Self-Supervised Training of Vision Transformers by Rotation Prediction

LSPP. Official PyTorch Implementation of Label Smoothing++: Enhanced Label Regularization for Training Neural Networks.

Glocal. Official PyTorch Implementation of Glocal Alignment for Unsupervised Domain Adaptation

Pytorch-NST. Pytorch implementation of Neural Style Transfer