From: Francois Fleuret Date: Mon, 29 Jun 2020 21:24:04 +0000 (+0200) Subject: Added README.md X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=commitdiff_plain;h=refs%2Fheads%2Fmaster;p=dyncnn.git Added README.md --- diff --git a/README.md b/README.md new file mode 100644 index 0000000..eaee433 --- /dev/null +++ b/README.md @@ -0,0 +1,33 @@ +# Description + +This is an attempt at predicting the dynamics of interacting objects +with a deep network. + +I wrote a simple 2d physics engine in C++ that simulates moment of +inertia, fluid frictions, and elastic collisions, and a residual +network in Lua/Torch that predicts the final configuration of a set of +rectangles, given a starting configuration and the location where a +force is applied. + +Results and analysis are available +in [`Fleuret (2016),`](https://fleuret.org/francois/publications.html#fleuret-2016) and you can have a look at +a [`2min video.`](https://fleuret.org/francois/files/fleuret-NIPS-intuitive-physics-spotlight.mp4) + +This package is composed of a simple 2d physics simulator called +'flatland' written in C++, to generate the data-set, and a deep +residual network 'dyncnn' written in the Lua/Torch7 framework. + +You can run the reference experiment by executing the `run.sh` shell +script. + +It will + +1. Generate the data-set of 40k triplets of images, + +2. Train the deep network, and output validation results every 100 + epochs. This takes ~30h on a GTX 1080 with cuda 8.0, cudnn 5.1, and + recent torch. + +3. Generate two pictures of the internal activations. + +4. Generate a graph with the loss curves if gnuplot is installed. diff --git a/README.txt b/README.txt deleted file mode 100644 index 1852663..0000000 --- a/README.txt +++ /dev/null @@ -1,32 +0,0 @@ - -This is an implementation of a deep residual network for predicting -the dynamics of 2D shapes as described in - - F. Fleuret. Predicting the dynamics of 2d objects with a deep - residual network. CoRR, abs/1610.04032, 2016. - - https://arxiv.org/abs/1610.04032 - -This package is composed of a simple 2d physics simulator called -'flatland' written in C++, to generate the data-set, and a deep -residual network 'dyncnn' written in the Lua/Torch7 framework. - -You can run the reference experiment by executing the run.sh shell -script. - -It will - - (1) Generate the data-set of 40k triplets of images, - - (2) Train the deep network, and output validation results every 100 - epochs. This takes ~30h on a GTX 1080 with cuda 8.0, cudnn 5.1, - and recent torch. - - (3) Generate two pictures of the internal activations. - - (4) Generate a graph with the loss curves if gnuplot is installed. - --- -Francois Fleuret -Nov 24, 2016 -Martigny