Pinned Repositories
adversarial-autoencoders
Sklearn compatible estimators for securing deep learning models from malicious attacks.
BoilerBot
Indoor delivery bot
domain-align
Original Source code for our paper: Unsupervised Domain Alignment to Mitigate low-level Dataset Biases
efficientCamScan
An implementation: https://nomis80.org/ctmf.pdf in C (pthreads have been used instead of SMID instructions).
observer-networks
Non-Intrusive Detection of Adversarial Deep Learning Attacks via Observer Networks
super-res
An extension of perpetual losses for image-inpainting. (https://arxiv.org/pdf/1603.08155.pdf)
Transfer-image-styling
This project uses the VGG-19 network to transfer the style/texture of an image onto the content of another image. Implementation of Neural style transfer.
TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in both training and inference.
TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.
ksivaman's Repositories
ksivaman/adversarial-autoencoders
Sklearn compatible estimators for securing deep learning models from malicious attacks.
ksivaman/Transfer-image-styling
This project uses the VGG-19 network to transfer the style/texture of an image onto the content of another image. Implementation of Neural style transfer.
ksivaman/super-res
An extension of perpetual losses for image-inpainting. (https://arxiv.org/pdf/1603.08155.pdf)
ksivaman/domain-align
Original Source code for our paper: Unsupervised Domain Alignment to Mitigate low-level Dataset Biases
ksivaman/TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in both training and inference.
ksivaman/efficientCamScan
An implementation: https://nomis80.org/ctmf.pdf in C (pthreads have been used instead of SMID instructions).
ksivaman/observer-networks
Non-Intrusive Detection of Adversarial Deep Learning Attacks via Observer Networks
ksivaman/You-Only-Look-Once
A PyTorch Object detector inspired by the YOLO algorithm
ksivaman/BoilerBot
Indoor delivery bot
ksivaman/accelerate
🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
ksivaman/adversarial-robustness-toolbox
Python library for adversarial attacks and defenses for neural networks, logistic regression, decision trees, SVM, gradient boosted trees, and more with multiple framework support
ksivaman/apex
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
ksivaman/ColossalAI
Making large AI models cheaper, faster and more accessible
ksivaman/DeepLearningExamples
Deep Learning Examples
ksivaman/ECE-463-Proj-2
How does sizeof work?
ksivaman/fast_adversarial
Code for the CVPR 2019 article "Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses"
ksivaman/flash-attention
Fast and memory-efficient exact attention
ksivaman/Hierarchical-clustering
A method to classify n dimensional data using hierarchical clustering
ksivaman/k-means-clustering
A method of clustering high dimension data using k-means clustering
ksivaman/linux
Linux kernel source tree
ksivaman/Megatron-LM
Ongoing research training transformer models at scale
ksivaman/miniCamScan
An algorithms that performs input image denoising using mean kernel filtering and adaptive thresholding.
ksivaman/opencv
Open Source Computer Vision Library
ksivaman/periflow-python-sdk
PeriFlow Python SDK
ksivaman/Purdue-Coursework
Repository of Purdue coursework.
ksivaman/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
ksivaman/scikit-learn
scikit-learn: machine learning in Python
ksivaman/SmartCityApp
Smart City App for the Smart City Project in Purdue University
ksivaman/thermocouple-data-analysis
Analysis of 5 types of thermocouple designs for First Order Systems Inc.
ksivaman/TransformerEngine-1
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in both training and inference.