GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → yihui-he → Exemplar Cnn

yihui-he / Exemplar Cnn

Discriminative Unsupervised Feature Learning with Convolutional Neural Networks

Programming Languages

matlab
3953 projects

Labels

cnn

Projects that are alternatives of or similar to Exemplar Cnn

Mvision
机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶
Stars: ✭ 6,140 (+38275%)
Mutual labels:  cnn
Dlib face recognition from camera
Detect and recognize the faces from camera / 调用摄像头进行人脸识别，支持多张人脸同时识别
Stars: ✭ 719 (+4393.75%)
Mutual labels:  cnn
Sincnet
SincNet is a neural architecture for efficiently processing raw audio samples.
Stars: ✭ 764 (+4675%)
Mutual labels:  cnn
Text Classification
Implementation of papers for text classification task on DBpedia
Stars: ✭ 682 (+4162.5%)
Mutual labels:  cnn
Pytorchinsight
a pytorch lib with state-of-the-art architectures, pretrained models and real-time updated results
Stars: ✭ 713 (+4356.25%)
Mutual labels:  cnn
Lstm Char Cnn Tensorflow
in progress
Stars: ✭ 737 (+4506.25%)
Mutual labels:  cnn
Cnn For Image Retrieval
🌅The code of post "Image retrieval using MatconvNet and pre-trained imageNet"
Stars: ✭ 597 (+3631.25%)
Mutual labels:  cnn
Quickdraw
Implementation of Quickdraw - an online game developed by Google
Stars: ✭ 805 (+4931.25%)
Mutual labels:  cnn
Tensorflow cookbook
Code for Tensorflow Machine Learning Cookbook
Stars: ✭ 5,984 (+37300%)
Mutual labels:  cnn
Srgan Tensorflow
Tensorflow implementation of the SRGAN algorithm for single image super-resolution
Stars: ✭ 754 (+4612.5%)
Mutual labels:  cnn
Ultra Fast Lane Detection
Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)
Stars: ✭ 688 (+4200%)
Mutual labels:  cnn
Torchio
Medical image preprocessing and augmentation toolkit for deep learning
Stars: ✭ 708 (+4325%)
Mutual labels:  cnn
Self driving pi car
A deep neural network based self-driving car, that combines Lego Mindstorms NXT with the computational power of a Raspberry Pi 3.
Stars: ✭ 744 (+4550%)
Mutual labels:  cnn
Prototypical Networks For Few Shot Learning Pytorch
Implementation of Prototypical Networks for Few Shot Learning (https://arxiv.org/abs/1703.05175) in Pytorch
Stars: ✭ 669 (+4081.25%)
Mutual labels:  cnn
Tf cnnvis
CNN visualization tool in TensorFlow
Stars: ✭ 769 (+4706.25%)
Mutual labels:  cnn
Cvnd exercises
Exercise notebooks for CVND.
Stars: ✭ 622 (+3787.5%)
Mutual labels:  cnn
Bosssensor
Hide screen when boss is approaching.
Stars: ✭ 6,081 (+37906.25%)
Mutual labels:  cnn
Ai sudoku
GUI based Smart Sudoku Solver that tries to extract a sudoku puzzle from a photo and solve it
Stars: ✭ 830 (+5087.5%)
Mutual labels:  cnn
Codes For Lane Detection
Learning Lightweight Lane Detection CNNs by Self Attention Distillation (ICCV 2019)
Stars: ✭ 801 (+4906.25%)
Mutual labels:  cnn
Tensorflow Tutorial
TensorFlow and Deep Learning Tutorials
Stars: ✭ 748 (+4575%)
Mutual labels:  cnn
View All Similar Projects ➔

Code used in the paper "Discriminative Unsupervised Feature Learning with Convolutional Neural Networks", NIPS 2014

Copyright (c) 2014 Alexey Dosovitskiy

Terms of use

The code is provided for research purposes only. Any commercial use is prohibited. If you are interested in a commercial use, please contact the copyright holder.

If you used this program in your research work, you should cite the following publication:

Alexey Dosovitskiy, Jost Tobias Springenberg, Martin Riedmiller and Thomas Brox, Discriminative Unsupervised Feature Learning with Convolutional Neural Networks, Advances in Neural Information Processing Systems 27 (NIPS 2014).

The code is distributed WITHOUT ANY WARRANTY.

Dependencies

For network training and testing we used Caffe software ( http://arxiv.org/abs/1408.5093, http://caffe.berkeleyvision.org/ ), this is a must-have dependency.

For testing you'll also need liblinear ( http://www.csie.ntu.edu.tw/~cjlin/liblinear/ )

For Spatial Pyramid Pooling (when testing on Caltech-101) we used pooling code from Matthew Zeiler's Adaptive Deconvolutional Networks ( http://www.matthewzeiler.com/ ). This can also in principle be done using caffe or some matlab code.

Description

We provide code for creating the training data, training and testing of the networks; as well as network configuration files and pre-trained networks.

For training a network, see code/training/demo_train_net.sh ( after correcting some paths in the demo and in train_nn_pretrain.sh ). The script allows pretraining with a diferent number of classes, which we do not actually need any more.

For testing, see code/testing/demo_test_net.m (matlab), you also need to correct some paths and download some datasets.

For dataset creation, see code/make_data/augment_patches_distr.m .

For converting data from matlab to leveldb or lmdb, see code/training/demo_convert_data.sh ( after correcting some paths in convert_data.sh ).

The configuration files include 'template' files which should be used with train_nn_pretrain.sh script, and test.prototxt files which may be used for testing with a pretrained network. Some of the files are in 'old' format which was previously used by caffe.

Bugs

Please report any bugs to Alexey Dosovitskiy ( [email protected] )

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].