Shreyas Daniel Gaddam's repositories
VisionGPT2
Combining ViT and GPT-2 for image captioning. Trained on MS-COCO. The model was implemented mostly from scratch.
shakespeareGPT
understanding language modeling by training a small GPT on Shakespeare plays.
yolo-object-detection-kitti
2D object detection for KITTI dataset finetuned using Ultralytics YOLOv8
bible-verse-search-app
semantically search Bible verses using NLP: https://bible-verse-search.streamlitapp.com/
youtube-in-video-search
YouTube Question-Answering and Semantic Search.
Machine_Learning_Models_from_scratch
linear regression, logistic regression, KNN classifier, ...
scratchformers
building various transformer model architectures and its modules from scratch.
transfer-learning
Transfer Learning Projects
hackerfeed
a simple decent material you style hackernews feed since the webpage sucks on mobile
Hebron-Verses-Generator
Hebron Calendar verses image generator : scripture.api.bible API -> JSON calendar -> static webpage with verse -> chrome headless screenshots
masked-language-modeling
Transformers Pre-Training with MLM objective — implemented encoder-only model and trained from scratch on Wikipedia dataset.
monocular-depth-estimation
monocular depth estimation using UNet-style architecture trained on NYUv2 depth dataset
multilingual-translation
Training a transformer for multilingual translation from scratch. Translates English to Hindi or Telugu. Trained on the Opus100 dataset for learning purposes.
pytorch-CNN-image-models
rough implementation of well-known CNN Image models in pytorch
shreydan.github.io
links page
binary-semantic-segmentation
binary semantic segmentation using UNet on CamVid dataset
computer-graphics-algorithms
computer graphics | P5.js implementations | SEM-V
computer-vision-course
This repo is the homebase of a community driven course on Computer Vision with Neural Networks. Feel free to join us on the Hugging Face discord: hf.co/join/discord
FLamby
Cross-silo Federated Learning playground in Python. Discover 7 real-world federated datasets to test your new FL strategies and try to beat the leaderboard.
jetson-nano-config
Nvidia Jetson Nano Configuration
ml-mobileone
This repository contains the official implementation of the research paper, "An Improved One millisecond Mobile Backbone".
onnx-mnist
basic onnx model on web using onnxwebruntime
paint-with-words-sd
Implementation of Paint-with-words with Stable Diffusion : method from eDiffi that let you generate image from text-labeled segmentation map.
vanilla-unet
u-net implementation as per: https://arxiv.org/abs/1505.04597