Skip to content

Ubuntu fix #31

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Alikerin wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Ubuntu fix #31

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c7168ca
Added code to fix Ubuntu issue
Alikerin Jul 8, 2020
a1f90ae
added .sh to setup_environment.sh in carla_challenge_coil_baseline.md
Alikerin Jul 10, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 13 additions & 16 deletions docs/carla_challenge_coil_baseline.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ Running the Baseline

Clone the repository:

git clone https://github.com/felipecode/coiltraine.git
git clone https://github.com/felipecode/coiltraine.git
cd coiltraine

We provide a conda environment requirements file, to
Expand All @@ -35,6 +35,12 @@ install and activate, just run:
conda env create -f requirements.yaml
conda activate coiltraine

Should in case you get the error `CMake must be installed to build the following extensions: dlib` on Ubuntu, run the following:

sudo apt-get install build-essential cmake
sudo apt-get install libgtk-3-dev
sudo apt-get install libboost-all-dev

Download the agent pytorch checkpoint by running the following script:

python3 tools/download_sample_models.py
Expand All @@ -53,14 +59,14 @@ Install the latest CARLA API:
Make sure you set the PYTHONPATH PythonAPI path:

export PYTHONPATH=${CARLA_ROOT}/PythonAPI/carla:$PYTHONPATH


### Visualize the agent results

### Visualize the agent results

First have the latest version of CARLA executing at some terminal at 40 fps (Recommend)

sh CarlaUE4.sh Town03 -windowed -world-port=2000 -benchmark -fps=40


To run the and visualize the model run:

Expand All @@ -75,22 +81,22 @@ layers. You can command a destination for the agent by using the arrow keys from


Clone the scenario runner repository:

cd
git clone -b carla_challenge https://github.com/carla-simulator/scenario_runner.git

Setup the scenario runner challenge repository by setting the path to your CARLA root
folder.

cd scenario_runner
bash setup_environment --carla-root <path_to_carla_root_folder>
bash setup_environment.sh --carla-root <path_to_carla_root_folder>


Export the coiltraine path to the PYTHONPATH:

cd ~/coitraine
export PYTHONPATH=`pwd`:$PYTHONPATH

Start the CARLA server on another terminal:

./CarlaUE4.sh -benchmark -fps=20 -quality-level=Epic
Expand Down Expand Up @@ -129,12 +135,3 @@ basic dataset:

To check images and train curves there is also a tensorboard log
being saved at "_logs" folder on the repository root.