Mirrors_Framework/deepmind-research
1
0
Fork 0
mirror of https://github.com/google-deepmind/deepmind-research.git synced 2026-05-30 20:35:25 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Internal

Browse Source 
PiperOrigin-RevId: 275055018
This commit is contained in:
Sebastian Borgeaud
2019-10-16 18:01:10 +01:00
committed by Diego de Las Casas
parent 8a9c3685af
commit e4ac909df7
1 changed files with 9 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
transporter/README.md
+9 -1
View File
@@ -1,7 +1,9 @@
# Transporter - Unsupervised Learning of Object Keypoints for Perception and Control # Transporter - Unsupervised Learning of Object Keypoints for Perception and Control
This directory contains a [Sonnet](https://sonnet.dev) implementation of This directory contains a [Sonnet](https://sonnet.dev) implementation of
the Transporter architecture. the Transporter architecture and a notebook explaining how the model can be used
for keypoint inference. To launch the notebook in Google colab, [click here](https://colab.research.google.com/github/deepmind/deepmind_research/blob/master/transporter/transporter_example.ipynb).
The Transporter is a neural network architecture for discovering concise The Transporter is a neural network architecture for discovering concise
geometric object representations in terms of keypoints or image-space geometric object representations in terms of keypoints or image-space
@@ -13,6 +15,9 @@ across long time-horizons more accurately than recent similar methods.
For details, see our For details, see our
paper [Unsupervised Learning of Object Keypoints for Perception and Control](https://arxiv.org/abs/1906.11883). paper [Unsupervised Learning of Object Keypoints for Perception and Control](https://arxiv.org/abs/1906.11883).
If you use the code here please cite this paper.
> Tejas Kulkarni, Ankush Gupta, Catalin Ionescu, Sebastian Borgeaud, Malcolm Reynolds, Andrew Zisserman, Volodymyr Mnih. *Unsupervised Learning of Object Keypoints for Perception and Control*. NeurIPS 2019. [\[arXiv\]](https://arxiv.org/abs/1906.11883).
## Contributors ## Contributors
* Tejas Kulkarni <tkulkarni@google.com> * Tejas Kulkarni <tkulkarni@google.com>
* Ankush Gupta <ankushgupta@google.com> * Ankush Gupta <ankushgupta@google.com>
@@ -23,3 +28,6 @@ paper [Unsupervised Learning of Object Keypoints for Perception and Control](htt
* Volodymyr Mnih * Volodymyr Mnih
## Disclaimer
This is not an official Google product.