fcn

CNNs library

An implementation of fully convolutional networks in Chainer, a deep learning framework.

Chainer Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

GitHub

218 stars
15 watching
97 forks
Language: Python
last commit: almost 5 years ago
Linked from 1 awesome list

chainercomputer-visionconvolutional-networksdeep-learningfcnfcn8ssegmentationsemantic-segmentation

Backlinks from these awesome lists:

Related projects:

RepositoryDescriptionStars
benedekrozemberczki/mixhop-and-n-gcnA deep learning framework implementation of higher-order graph convolutional architectures and their applications403
ahmedfgad/numpycnnA Python implementation of a Convolutional Neural Network from scratch using NumPy for building CNNs from scratch577
eilene/gwnnA TensorFlow implementation of a graph convolution algorithm using wavelet transforms instead of traditional methods.64
preritj/segmentationDeep learning models for semantic segmentation of images101
theduynguyen/keras-fcnAn implementation of fully convolutional neural networks for semantic segmentation using TensorFlow as the backend.15
simonguist/testing-fcn-for-cityscapesAn implementation of fully convolutional networks for semantic segmentation using the Cityscapes dataset and Caffe deep learning framework.27
apple2373/chainer-simple-fast-rnnAn implementation of the fast R-CNN object detection algorithm using Chainer and OpenCV.43
jihongju/keras-fcnA library implementing a Fully Convolutional Network architecture with Keras support202
doonny/pipecnnA tool for accelerating convolutional neural networks on Field-Programmable Gate Arrays (FPGAs) using OpenCL-based hardware design1,264
muyang0320/tf-fcnA basic implementation of a fully convolutional network (FCN) for image segmentation in TensorFlow.9
ibbm/cascaded-fcnAn implementation of a Cascaded Fully Convolutional Neural Network architecture for medical image segmentation304
ahmedfgad/cnngeneticTrains CNNs using a genetic algorithm for classification problems where one class per sample is allowed.22
mattya/chainer-dcganGenerates images using a Deep Convolutional Generative Adversarial Network (DCGAN) algorithm936
nv-tlabs/gscnnThis code implements a neural network architecture designed to perform semantic segmentation in computer vision tasks.920
matenure/fastgcnImplementation of graph convolutional network algorithms with sampling techniques to improve learning speed and efficiency520