Jack Turner's repositories
deep-compression
Learning both Weights and Connections for Efficient Neural Networks https://arxiv.org/abs/1506.02626
pytorch-onnx-tvm
PyTorch -> ONNX -> TVM for autotuning
nas-as-program-transformation-exploration
The code for our paper "Neural Architecture Search as Program Transformation Exploration"
gymnastics
A "gym" style toolkit for building lightweight NAS systems.
the-torch-bench
A personal tool for benchmarking PyTorch things.
AutoDL-Projects
Automated deep learning algorithms implemented in PyTorch.
coffee-spiders
Replicating the Artisan Roast coffee charts
creative-matplotlib
Assorted creative coding scripts & outputs using vanilla matplotlib
fbnet_without_training
Searching the FBNet search space with NASWOT
jack-willturner.github.io
Website.
nas-without-training
Code for Neural Architecture Search without Training (ICML 2021)
nn_design_patterns
An exploration of design patterns for constructing neural networks.
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2, MNASNet, Single-Path NAS, FBNet, and more
tvm_groupconv
A naive implementation of group convolution in TVM compute syntax