Gyanateet Dutta's repositories
Self.Diffusion
Python scripts or notebooks of different implementation of small scale diffusion networks for prototyping and then experimented with different datasets.
ESRGAN_AND_YOLOV7
Implementation for the final year project and the paper Improved Pothole Detection Using ESRGAN and YOLOv7
-Transformers-
Implementations of different Transformers on a variety of problems.
OPEN_GL_Graphics_Programming
This repository contains the OpenGL programs and builds I made.
cudawesome
A collection of awesome algorithms, implemented in CUDA.
Graph-Neural-Networks-
Implementations of popular Graph Neural Network models in PyTorch/TensorFlow/Jax
JAXploration
Dive deep into the world of Machine Learning with the JAX framework! 🚀 This repository houses my learning journey, experiments, and implementations of cutting-edge papers and projects using JAX. Join me as I unravel the power and flexibility of JAX in ML! 🧠💡
audio-diffusion
Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead of images.
bitsandbytes
8-bit CUDA functions for PyTorch
CatCon-Controlnet-WD-1-5-b2
Experimental proof of concept made for the [Huggingface JAX/Diffusers community sprint](https://github.com/huggingface/community-events/tree/main/jax-controlnet-sprint)
cicd_forml_test
Learning how to create ci-cd tests for ml
Gradio_app_scripts_notebooks
Scripts and notebooks for gradio apps for huggingface spaces.
IF
Deep Floyd IF
Jax-Flax-Haiku
Repo contains notebooks of diffusion models and transformers implemented in the frameworks the repo is named after.
Mojo-jojo
This repository is dedicated to my learning journey with the Mojo language. It contains a collection of programs written in Mojo as I explore its syntax, semantics, and capabilities. Whether you’re a fellow learner or an experienced Mojo programmer, feel free to explore, contribute, and provide feedback. Let’s master Mojo together
Physics-Based-DeepLearning
Dedicated to exploring the intersection of physics and machine learning.
Programming_for_data_science_project
OWO UWU. What are you guys looking for?
Pytorch_3d_ryu
Work in progress.
Pytorch_xla
tutorial_notebooks and pytorch self implementations done on the tpu.
r2d2
Implementation of R2D2 algorithm
sleap
A deep learning framework for multi-animal pose tracking.
SoulsGym
OpenAI gym extension for DarkSouls III
tapnet
TAPIR is a two-stage algorithm which employs two stages: 1) a matching stage, which independently locates a suitable candidate point match for the query pointon every other frame, and (2) a refinement stage, which updates both the trajectory and query features based on local correlations. The resulting model is fast and surpasses all prior methods