ginvermouth's starred repositories
the-art-of-command-line
Master the command line, in one page
efficient_densenet_pytorch
A memory-efficient implementation of DenseNets
pytorch_tiramisu
FC-DenseNet in PyTorch for Semantic Segmentation
pytorch-classification
Classification with PyTorch.
Multichannel_Image_Pytorch_Dataset
A Dataset that supports images with an arbitrary number of channels for both inputs and outputs for image segmentation
connected-components-3d
Connected components on discrete and continuous multilabel 3D & 2D images. Handles 26, 18, and 6 connected variants; periodic boundaries (4, 8, & 6)
3d-nii-visualizer
A NIfTI (nii.gz) 3D Visualizer using VTK and Qt5
MICCAI-LITS2017
liver segmentation using deep learning
vnet.pytorch
A PyTorch implementation for V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
vnet-tensorflow
Implementation of vnet in tensorflow for medical image segmentation
fcn.berkeleyvision.org
Fully Convolutional Networks for Semantic Segmentation by Jonathan Long*, Evan Shelhamer*, and Trevor Darrell. CVPR 2015 and PAMI 2016.
tensorflow
An Open Source Machine Learning Framework for Everyone
Faster-RCNN-TensorFlow-Python3
Tensorflow Faster R-CNN for Windows/Linux and Python 3 (3.5/3.6/3.7)
tensorflow-deeplab-v3-plus
DeepLabv3+ built in TensorFlow
deeplab_v3
Tensorflow Implementation of the Semantic Segmentation DeepLab_V3 CNN
A-Variation-of-Dice-coefficient-Loss-Caffe-Layer
Compute the variation of dice coefficient loss for real-value regression task.
caffe-segnet
Implementation of SegNet: A Deep Convolutional Encoder-Decoder Architecture for Semantic Pixel-Wise Labelling
caffe-segnet-cudnn5
This repository was a fork of BVLC/caffe and includes the upsample, bn, dense_image_data and softmax_with_loss (with class weighting) layers of caffe-segnet (https://github.com/alexgkendall/caffe-segnet) to run SegNet with cuDNN version 5.
Caffe-Python-Basic-Tutorial
Includes implementation details of almost every layer, weight fillers, solvers, loss functions and data layer setup with every parameter.