jgraving

dsnt

A Tensorflow implementation of the DSNT layer, as taken from the paper "Numerical Coordinate Regression with Convolutional Neural Networks".

360Controller

TattieBogle Xbox 360 Driver (with improvements)

bayesian_bootstrap

bayesian bootstrapping in python

cheatsheets-ai

Essential Cheat Sheets for deep learning and machine learning researchers

DEC-keras

Keras implementation for Deep Embedding Clustering (DEC)

deep-motion-analysis

Motion analysis using deep neural networks

drn

Dilated Residual Networks

enzynet

EnzyNet: enzyme classification using 3D convolutional neural networks on spatial representation

face_classification

Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.

FastMaskRCNN

Mask RCNN in TensorFlow

GatedPixelCNNPyTorch

PyTorch implementation of "Conditional Image Generation with PixelCNN Decoders" by van den Oord et al. 2016

IDEC-toy

information-bottleneck

a python implementation of various versions of the information bottleneck, including automated parameter searching

keras-fcn-1

A re-implementation of Fully Convolutional Networks with Keras.

keras-molecules

Autoencoder network for learning a continuous representation of molecular structures.

keras-rcnn

Keras package for region-based convolutional neural networks

keras-visualize-activations

MNIST example to show how to get the activations for each layer in Keras.

Mask_RCNN

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

nonlinearIB

Nonlinear Information Bottleneck

pose-hg-demo

Code to test and use the model from "Stacked Hourglass Networks for Human Pose Estimation"

Probabilistic-Programming-and-Bayesian-Methods-for-Hackers

aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

Radon-Transform_Schultz-Gu

We present two Matlab-based routines, Radon_inverse and Radon_forward, that perform discrete inverse and forward Radon transforms. These frequency-based methods offer the user flexible choices among multiple regularization methods and path functions. They are designed for simplicity and flexibility, and the Matlab foundation ensures portability between platforms. Both Radon_inverse and Radon_forward could be readily adapted or modified for a broad range of geophysical applications.

retina-unet

Retina blood vessel segmentation with a convolutional neural network

scikit-image

Image Processing SciKit (Toolbox for SciPy)

Splines_in_Stan

Implementation of B-Splines in Stan

ssd.pytorch

A PyTorch Implementation of Single Shot MultiBox Detector

tensortools

Fitting and visualizing tensor decompositions in Python

unet-keras

U-Net model for Keras

unet-tensorflow-keras

A concise code for training and evaluating Unet using tensorflow+keras

vib_demo