This is an implementation of a deep residual network for predicting
-the dynamics of 2D shapes.
+the dynamics of 2D shapes as described in
-This package is composed of two main parts: 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.
+ 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 generate the data-set of 50k triplets of images, train
-the deep network, and output validation results every 100 epochs.
+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
-Oct 7, 2016
+Nov 24, 2016
Martigny