briando2005 Goto Github PK

kaggle-ds-bowl-2018-baseline

Full train/inference/submission pipeline adapted to the competition from https://github.com/matterport/Mask_RCNN

kaggle-heart

kaggle-ndsb

Winning solution for the National Data Science Bowl competition on Kaggle (plankton classification)

kaggle_ndsb2

3rd place solution for the second kaggle national datascience bowl

kaggle_ndsb2017

Kaggle datascience bowl 2017

keras

Deep Learning library for Python. Runs on TensorFlow, Theano, or CNTK.

keras-adversarial

Keras Generative Adversarial Networks

keras-cam

Keras implementation of class activation mapping

keras-deeplab-v3-plus

Keras implementation of Deeplab v3+ with pretrained weights

keras-gcnn

Roto-reflection equivariant CNNs for Keras as presented in B. S. Veeling, J. Linmans, J. Winkens, T. Cohen, M. Welling. "Rotation Equivariant CNNs for Digital Pathology".

keras-grad-cam

An implementation of Grad-CAM with keras

keras-resources

Directory of tutorials and open-source code repositories for working with Keras, the Python deep learning library

keras-spp

Spatial pyramid pooling layers for keras

keras-tcn

Keras Temporal Convolutional Network.

keras-vis

Neural network visualization toolkit for keras

knee-mri-segmentation

Thesis & Code for my Segmentation and Age Prediction Model using CNNs and MRIs

knowledge-repo

A next-generation curated knowledge sharing platform for data scientists and other technical professions.

label-ai

labelml

Machine Learning Image Annotation Tool

lasc

Left Atrial Segmentation Challenge 2013

learn_python_libraries

Exploring most useful libraries of Python. Each notebook covers basic and advanced functionalities of a python library.

lede-algorithms

Algorithms course materials for the Lede program at Columbia Journalism School

lemaitre-2016-nov

lime

LiME (formerly DMD) is a Loadable Kernel Module (LKM), which allows the acquisition of volatile memory from Linux and Linux-based devices, such as those powered by Android. The tool supports acquiring memory either to the file system of the device or over the network. LiME is unique in that it is the first tool that allows full memory captures from Android devices. It also minimizes its interaction between user and kernel space processes during acquisition, which allows it to produce memory captures that are more forensically sound than those of other tools designed for Linux memory acquisition.

lime-1

Lime: Explaining the predictions of any machine learning classifier

loss_kaggle_2018

Investigation of focal and dice loss for the Kaggle 2018 data science bowl.

lowrankismrm

Low rank image reconstruction tutorial from ISMRM 2018

lstm

lucid

A collection of infrastructure and tools for research in neural network interpretability.

lung-segmentation-2d

Lung fields segmentation on CXR images using convolutional neural networks.