The fastai deep learning library

Distributed deep learning on Hadoop and Spark clusters.

D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

Enabling journalists, citizen scientists, humanitarian workers and others to detect “patterns of interest” in satellite imagery.

Accelerating Deep Learning with Multiprocess Image Augmentation in Keras

TensorFlow Metal Backend on Apple Silicon Experiments (just for fun)

Implementation of spatial transformer networks (STNs) in keras 2 with tensorflow as backend.

Weakly Supervised Segmentation with Tensorflow. Implements instance segmentation as described in Simple Does It: Weakly Supervised Instance and Semantic Segmentation, by Khoreva et al. (CVPR 2017).

PyTorch code for Neighbourhood Consensus Networks

Process and export Jupyter Notebooks fast (Jupyter not required)