KENTARO WADA

Thank you for visiting. This is my personal page.

Software

Open source projects which I developed or contributed to.


Deep Learning + Computer Vision

Image Polygonal Annotation with Python (polygon, rectangle, line, point and image-level flag annotation).

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

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

Chainer Implementation of Mask R-CNN. (Training code to reproduce the original result is available.)

Toolkit for PASCAL3D dataset.

Image augmentation for machine learning experiments.


Deep Learning + Computer Graphics

Chainer implementation of "Toward Multimodal Image-to-Image Translation".

Chainer implementation of "Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Network".

Transgender of real persons to achieve real harem, with mixed reality on Hololens.


Deep Learning Library

A flexible framework of neural networks for deep learning

NumPy-like API accelerated with CUDA


Computer Vision + Robotics

Volumetric Fusion of Multiple Semantic Labels and Masks

JSK perception ROS packages

jsk visualization ros packages

PCL (Point Cloud Library) ROS interface stack

ROS communications-related packages, including core client libraries (roscpp, rospy, roslisp) and graph introspection tools (rostopic, rosnode, rosservice, rosparam).

Allows one to create "nodelets" -- ROS node-like entities that run within the same process so as to avoid IPC and serialization overhead


Utility

Download a large file from Google Drive (curl/wget fails because of the security notice).

Navigate in Google Drive as you do on shell (gshell = Google Drive + Shell).

`cd` to python modules.

`cd` to repos in workspace managed by wstool.

See Gotenshita(御殿下) court open status.

Contact to me! :)