Harikrishnan Seetharaman's repositories
Analysis-of-GAN-approaches-on-MNIST-using-TF2.0
The Generative Adversarial Networks with Python would serve as our primary reference throughout the project. The models would be trained on the MNIST dataset. The official TensorFlow framework and documentation will be used to implement the different architectures on Python. These papers would be used to implement various evaluation met
RL_DQN_Planar_Pushing_ABB
Implementation of DQN Network in ABB YuMi Manipulator to do planar pushing under external perturbance.
curobo
CUDA Accelerated Robot Library
Deep-Learning-for-Robotics-Project
Contact-grasp net + Affordance Novelty
diff-gaussian-rasterization
CUDA-Rasterization-Forked
EECS-471-MXNet-Project
Private repo for EECS-471 Applied GPU Programming FInal Project. Goal is to perform optimization in the forward convolution pass using the MXNet Library and CUDA programming.
Face-Detection-Hackathon
Worked on creating a all in one solution for various sub problems of face detection which includes Blur detection , Professionalism check , Spoof detection , Watermark detection and Obstruction detection.
GAN-Pix2Pix
Training a GAN using Pix2Pix model to solve the image translation problem of converting satellite photos to Google maps and vice versa.
gaussian-splatting-pytorch
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
Machine-Learning
Here are all my projects in Machine Learning and Data Science.
Neural-ODE-Robot-Learning
Cartpole dynamics prediction using neural ode solver with Gym space.
HariKrishnan06082k
Profile Description
Introduction-to-Manipulation
Python scripts of the assignments in ROB 599 Introduction to Manipulation (Fall 2023)
LLFF
Code release for Local Light Field Fusion at SIGGRAPH 2019
NeRF-Reflection
Code release for NeRFReN: Neural Radiance Fields with Reflections (CVPR 2022).
PoseCNN
PyTorch implementation of PoseCNN
RL-grid
Reinforcement learning DQN Implementation to drive agent to goal in desired trajectory. Custom Gym space for 3x3 Grid.
Robot-Learning-for-Planning-and-Control
Topics include function approximation, learning dynamics, using learned dynamics in control and planning, handling uncertainty in learned models, learning from demonstration, and model-based and model-free reinforcement learning.
Two-Stage-Object-Detector-Faster-R-CNN
Object Detector Faster RCNN with Feature Pyramid Network and RegNetX-400MF as the backbone.