added example checkpoint for kitti dataset

leggedrobotics · May 24, 2021 · bb7205d · bb7205d
1 parent 31d357f
commit bb7205d
Show file tree

Hide file tree

Showing 10 changed files with 24 additions and 2 deletions.
diff --git a/.gitattributes b/.gitattributes
@@ -0,0 +1 @@
+*.pth filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
@@ -9,8 +9,10 @@ This is the corresponding code to the above paper ("Self-supervised Learning of
 Applications") which is published at the International Conference on Robotics and Automation (ICRA) 2021. The code is
 provided by the [Robotics Systems Lab](https://rsl.ethz.ch/) at ETH Zurich, Switzerland.
 
-**Authors:** [Julian Nubert](https://juliannubert.com/) ([[email protected]](mailto:[email protected]?subject=[GitHub]))
-, [Shehryar Khattak](https://www.linkedin.com/in/shehryar-khattak/), [Marco Hutter](https://rsl.ethz.ch/the-lab/people/person-detail.MTIxOTEx.TGlzdC8yNDQxLC0xNDI1MTk1NzM1.html)
+**
+Authors:** [Julian Nubert](https://juliannubert.com/) ([[email protected]](mailto:[email protected]?subject=[GitHub]))
+, [Shehryar Khattak](https://www.linkedin.com/in/shehryar-khattak/)
+, [Marco Hutter](https://rsl.ethz.ch/the-lab/people/person-detail.MTIxOTEx.TGlzdC8yNDQxLC0xNDI1MTk1NzM1.html)
 
 ![title_img](images/title_img.png)
 
@@ -153,6 +155,8 @@ run_testing.py --checkpoint <path_to_checkpoint>
 The checkpoint can be found in MLFlow after training. It runs testing for the dataset specified
 in [./config/deployment_options.yaml](./config/deployment_options.yaml).
 
+We provide an exemplary trained model in [./checkpoints/kitti_example.pth](./checkpoints/kitti_example.pth).
+
 ### ROS-Node
 
 This ROS-node takes the pretrained model at location ```<model_location>``` and performs inference; i.e. it predicts and

diff --git a/checkpoints/README.md b/checkpoints/README.md
@@ -0,0 +1,14 @@
+# Example network trained on the KITTI dataset
+
+We provide an example network in ```kitti_example.pth```. Note that the checkpoint also includes the configuration of
+the trained model. When loading the model, the corresponding configuration is set automatically.
+
+The plots generated by the testing code for this model can be seen in the following:
+
+| Sequence 00 | Sequence 02 |
+| :---: | :---: |
+| ![Dataset 00](kitti_00_2d.png) | ![Dataset 02](kitti_02_2d.png) |
+| Sequence 05 | Sequence 07 |
+| ![Dataset 05](kitti_05_2d.png) | ![Dataset 08](kitti_07_2d.png) |
+| Sequence 08 | Sequence 10 |
+| ![Dataset 08](kitti_08_2d.png) | ![Dataset 10](kitti_10_2d.png) |
diff --git a/checkpoints/kitti_00_2d.png b/checkpoints/kitti_00_2d.png
diff --git a/checkpoints/kitti_02_2d.png b/checkpoints/kitti_02_2d.png
diff --git a/checkpoints/kitti_05_2d.png b/checkpoints/kitti_05_2d.png
diff --git a/checkpoints/kitti_07_2d.png b/checkpoints/kitti_07_2d.png
diff --git a/checkpoints/kitti_08_2d.png b/checkpoints/kitti_08_2d.png
diff --git a/checkpoints/kitti_10_2d.png b/checkpoints/kitti_10_2d.png
diff --git a/checkpoints/kitti_example.pth b/checkpoints/kitti_example.pth