alexhagiopol / Deep_homography_estimation
Compute homographies with deep networks instead of feature matching and RANSAC.
Stars: ✭ 40
Labels
Projects that are alternatives of or similar to Deep homography estimation
Word2vec Russian Novels
Inspired by word2vec-pride-vis the replacement of words of Russian most valuable novels text with closest word2vec model words. By Boris Orekhov
Stars: ✭ 39 (-2.5%)
Mutual labels: jupyter-notebook
Optical illusion
A simple optical illusion in python
Stars: ✭ 40 (+0%)
Mutual labels: jupyter-notebook
Deeplearning In Action
《深度学习原理与实践》相关代码——source code of the book <deep learning in action>
Stars: ✭ 40 (+0%)
Mutual labels: jupyter-notebook
Pixiedust
Python Helper library for Jupyter Notebooks
Stars: ✭ 998 (+2395%)
Mutual labels: jupyter-notebook
Hackathons solution
Find the solution of machine learning competitions I am participating.
Stars: ✭ 40 (+0%)
Mutual labels: jupyter-notebook
Netsci Project
Network Analysis for Financial Markets
Stars: ✭ 39 (-2.5%)
Mutual labels: jupyter-notebook
Cs231n 2017
My own solutions for Stanford CS231n (2017) assignments
Stars: ✭ 40 (+0%)
Mutual labels: jupyter-notebook
Nbgrader
A system for assigning and grading notebooks
Stars: ✭ 1,000 (+2400%)
Mutual labels: jupyter-notebook
Praatscripts
These are praat scripts I use in my research, implemented in parselmouth for python for use in binder
Stars: ✭ 40 (+0%)
Mutual labels: jupyter-notebook
Adversarial workshop
Adversarial Workshop code and presentation
Stars: ✭ 39 (-2.5%)
Mutual labels: jupyter-notebook
Cerndeeplearningtutorial
Introduction to root_numpy, pandas, Keras in simple Deep Learning application at CERN
Stars: ✭ 39 (-2.5%)
Mutual labels: jupyter-notebook
Intel Scene Classification
This is the 1st place solution for AV Intel scene classification challenge
Stars: ✭ 41 (+2.5%)
Mutual labels: jupyter-notebook
Multimodalsr
Multimodal speech recognition using lipreading (with CNNs) and audio (using LSTMs). Sensor fusion is done with an attention network.
Stars: ✭ 39 (-2.5%)
Mutual labels: jupyter-notebook
Meetups Data Ai Dfw
Content for Meetups for DATA & AI - Microsoft DFW
Stars: ✭ 39 (-2.5%)
Mutual labels: jupyter-notebook
Data utilities
Utilities for processing the xView 2018 dataset (i.e., xview1)
Stars: ✭ 40 (+0%)
Mutual labels: jupyter-notebook
Python101code
Code examples from the book, Python 101 by Michael Driscoll
Stars: ✭ 40 (+0%)
Mutual labels: jupyter-notebook
Deep Image Homography Estimation
Abstract
This project implements the 2016 paper Deep Image Homography Estimation by DeTone, Malisiewicz, and Rabinovich. We create an image homography training set by randomly warping the dataset presented in the 2015 paper Microsoft COCO: Common Objects in Context by Lin et al. We then architect and train a deep convolutional neural network to learn how to compute a 3x3 homography matrix given an image pair.
Installation
This procedure was tested on Ubuntu 16.04 and Mac OS X 10.11.6 (El Capitan). GPU-accelerated training is supported on Ubuntu only.
Prerequisites: Install Python package dependencies using my instructions. Then, activate the environment:
source activate deep-learning
Optional, but recommended on Ubuntu: Install support for NVIDIA GPU acceleration with CUDA v8.0 and cuDNN v5.1:
wget https://www.dropbox.com/s/08ufs95pw94gu37/cuda-repo-ubuntu1604-8-0-local-ga2_8.0.61-1_amd64.deb
sudo dpkg -i cuda-repo-ubuntu1604-8-0-local-ga2_8.0.61-1_amd64.deb
sudo apt-get update
sudo apt-get install cuda
wget https://www.dropbox.com/s/9uah11bwtsx5fwl/cudnn-8.0-linux-x64-v5.1.tgz
tar -xvzf cudnn-8.0-linux-x64-v5.1.tgz
cd cuda/lib64
export LD_LIBRARY_PATH=`pwd`:$LD_LIBRARY_PATH
cd ..
export CUDA_HOME=`pwd`
sudo apt-get install libcupti-dev
pip install --ignore-installed --upgrade https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow_gpu-1.1.0-cp35-cp35m-linux_x86_64.whl
Clone the deep_homography_estimation repo:
git clone https://github.com/alexhagiopol/deep_homography_estimation
cd deep_homography_estimation
Download the MSCOCO Dataset:
mkdir MSCOCO
cd MSCOCO
wget http://msvocds.blob.core.windows.net/coco2014/train2014.zip
wget http://msvocds.blob.core.windows.net/coco2014/val2014.zip
wget http://msvocds.blob.core.windows.net/coco2014/test2014.zip
wget http://msvocds.blob.core.windows.net/coco2015/test2015.zip
unzip *.zip
tar -xvzf traffic-signs-data.tar.gz
rm -rf traffic-signs-data.tar.gz
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].