Skanda Koppula's repositories
sid-ternary-network
Code and models to accompany "Energy Efficient SID for Low-Precision Networks"
speaker-auth-demo
speaker-auth-demo
rnn-from-scratch
Use tensorflow's tf.scan to build vanilla, GRU and LSTM RNNs
speaker-id-thesis
Experiments with various types of network weight/activation quantization and model compression, with focus on speaker ID models
zsim-ramulator
Back-up of an integration of architectural simulator zsim (https://github.com/s5z/zsim) with DRAM simulator RAMULATOR (https://github.com/CMU-SAFARI/ramulator)
amun
Fast stand-alone C++ decoder for RNN-based NMT models
craiglist-stolen-bike-tracker
Scraper to automate checking Craiglist's city-specific bicycles front page for your bike
Cutie
[arXiv 2023] Putting the Object Back Into Video Object Segmentation
decaf-compiler
Compiler for Decaf Language (C-like Language)
dinov2
PyTorch code and models for the DINOv2 self-supervised learning method.
dorefa-net
Arbitrary Bit Weight/Activation Quantization of Using DoReFa
dynamic_rnn_example
Code example for tf.nn.dynamic_rnn using Tensorflow library
gpgpu-sim_distribution
GPGPU-Sim provides a detailed simulation model of a contemporary GPU running CUDA and/or OpenCL workloads and now includes an integrated (and validated) energy model, GPUWattch.
kaldi
This is now the official location of the Kaldi project.
latex-resume
Rolling out the LaTeX resume.
models
Models built with TensorFlow
MQSim
MQSim is a fast and accurate simulator modeling the performance of modern multi-queue (MQ) SSDs as well as traditional SATA based SSDs. MQSim faithfully models new high-bandwidth protocol implementations, steady-state SSD conditions, and the full end-to-end latency of requests in modern SSDs. It is described in detail in the FAST 2018 paper by Arash Tavakkol et al., "MQSim: A Framework for Enabling Realistic Studies of Modern Multi-Queue SSD Devices" (https://people.inf.ethz.ch/omutlu/pub/MQSim-SSD-simulation-framework_fast18.pdf)
NoJunk
Chrome extension to remove ads/comments/hot network questions/autoreplay from StackOverflow & Youtube
skoppula.github.io
my static site
trained-ternary-quantization
Reducing the size of convolutional neural networks