Douwe den Blanken's repositories
brevitas-utils
Various utilities for the Brevitas (https://github.com/Xilinx/brevitas) framework for neural network quantization in PyTorch
autolightning
Automating PyTorch Lightning via simple yet expressive configurations
torch-mate
Various tools/utilities for PyTorch
TCN-library
This project builds on top of the TCN in https://github.com/locuslab/TCN and extends it with ResNeXt style blocks and depthwise separable convolutions.
pytorch-lightning
Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.
AudioLoader
PyTorch Dataset for Speech and Music audio
pymeasure
Scientific measurement library for instruments, experiments, and live-plotting
cnn.c
C implementation of basic CNN modules
parametrizable-floating-point-verilog
Verilog library that supports IEEE754 floating point arithmetic with a parametrizable mantissa and exponent
few-shot-spoken-term-classification
A quick reimplementation of the two datasets ("digits" and "commands") proposed in the paper "An Investigation of Few-Shot Learning in Spoken Term Classification"
verilog-array-operations
Verilog array operations like reshaping
causal-conv1d
Causal depthwise conv1d in CUDA, with a PyTorch interface
install-verilator-action
Install Verilator for use in a Github Action workflow
cs249r_book
Collaborative book for CS249r: Tiny Machine Learning
early-stopping
Early stopping for neural network training
neural-network-figures
This project contains various figures, diagrams and plots related to neural networks.
serverless-lambda-typescript-airbnb-eslint
AWS Lambda Serverless template, with AirBnB ESLint and Prettier setup :)
serverless-lambda-python3
AWS Lambda Serverless template for Python3 functions :)
brevitas
Brevitas: quantization-aware training in PyTorch
multilingual_kws
Few-shot Keyword Spotting in Any Language and Multilingual Spoken Word Corpus
verible-linter-action
Automatic SystemVerilog linting in github actions with the help of Verible
aimet
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
model_optimization
Model Compression Toolkit (MCT) is an open source project for neural network model optimization under efficient, constrained hardware. This project provides researchers, developers, and engineers advanced quantization and compression tools for deploying state-of-the-art neural networks.
QPyTorch
Low Precision Arithmetic Simulation in PyTorch
omniglot
Omniglot data set for one-shot learning
express-server-kill-after-inactivity
Simple Node.JS Express server which kills itself after inactivity. Can be bundled with the included Dockerfile.
chisel3
Chisel 3: A Modern Hardware Design Language