/VLNREM

Vision-Language Navigation with Random Environmental Mixup

Primary LanguageC++MIT LicenseMIT

Code and Data for Paper "Vision-Language Navigation with Random Environmental Mixup"


We have released the key code in ./REM, the specific details will be added in the future.


Environment Installation

Download Room-to-Room navigation data:

bash ./tasks/R2R/data/download.sh

Download image features for environments:

mkdir img_features
wget https://www.dropbox.com/s/o57kxh2mn5rkx4o/ResNet-152-imagenet.zip -P img_features/
cd img_features
unzip ResNet-152-imagenet.zip

Python requirements: Need python3.6 (python 3.5 should be OK since I removed the allennlp dependencies)

pip install -r python_requirements.txt

Install Matterport3D simulators:

git submodule update --init --recursive 
sudo apt-get install libjsoncpp-dev libepoxy-dev libglm-dev libosmesa6 libosmesa6-dev libglew-dev
mkdir build && cd build
cmake -DEGL_RENDERING=ON ..
make -j8