kentsommer/tensorflow-posenet

Stars
287
Rank 144,232 (Top 3 %)
Language
Python
License
MIT License
Created almost 8 years ago
Updated about 2 years ago

kentsommer/tensorflow-posenet

kentsommer

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Implementation of Posenet in TensorFlow

TensorFlow-PoseNet

This is an implementation for TensorFlow of the PoseNet architecture

As described in the ICCV 2015 paper PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization Alex Kendall, Matthew Grimes and Roberto Cipolla [http://mi.eng.cam.ac.uk/projects/relocalisation/]

Getting Started

Download the Cambridge Landmarks King's College dataset from here.
Download the starting weights from here.
The PoseNet model is defined in the posenet.py file
The starting weights (posenet.npy) for training were obtained by converting caffemodel weights from here.
To run:
- Extract the King's College dataset to wherever you prefer
- Extract the starting weights
- To train, simply run train.py after setting the path to the King's College dataset (note this will take a long time)
- After training, to test run test.py after updating the paths on these lines

keras-inceptionV4

Keras Implementation of Google's Inception-V4 Architecture (includes Keras compatible pre-trained weights)

pytorch-value-iteration-networks

Pytorch implementation of Value Iteration Networks (NIPS 2016 best paper)

VGG16-Image-Retrieval

Uses TensorFlow and FC2 features to match test images to the same category given a query image as input

keras-posenet

Implementation of the PoseNet Architecture in Keras

keras-inception-resnetV2

Keras implementation of Google's inception-resnet-v2 Architecture

py-unsubscribe

Automatic email unsubscriber in Python

2D-EKF-SLAM

Project for Introduction to Sensing and Estimation in Robotics

obstacle_detection

Detection stack using PCL and ROS.

3DObjectReconstruction

3D Static Object Reconstruction using Shape From Silhouette techniques

openni2

Setup description for Prime-sense(601) for use with ROS Xtion Pro

ros-rl-environment

Some helper scripts to get a ROS Kinetic RL development environment setup on a clean 16.04 install

Web-Based-ANN-Touch-Inference

Touch Location Inference on Mobile Devices Using the Accelerometer and Gyroscope.

hubo_slam_ws

Files for auto ws setup for hubo slam