diff --git a/README.md b/README.md index f4ad3f0d91805457339f590097b44b2eb7e7fd3e..5526eb1f74bc1a4bd7a4fa8b72b677c386a551f7 100644 --- a/README.md +++ b/README.md @@ -56,7 +56,7 @@ This repository is the official implementation of the [CVPR 2022](https://cvpr20 EMOCA takes a single in-the-wild image as input and reconstructs a 3D face with sufficient facial expression detail to convey the emotional state of the input image. EMOCA advances the state-of-the-art monocular face reconstruction in-the-wild, putting emphasis on accurate capture of emotional content. The official project page is [here](https://emoca.is.tue.mpg.de/index.html). ## !!! UPDATE !!! -**EMOCA v2 is now out.** Complete the installation steps below and o to [EMOCA](gdl_apps/EMOCA) to test the demos. +**EMOCA v2 is now out.** Complete the installation steps below and go to [EMOCA](gdl_apps/EMOCA) to test the demos. Compared to the original model it produces: diff --git a/install_38.sh b/install_38.sh index 071b52fb55bfd46bdaf5f6d250e7ddeb5b4c91a6..c38ea8643fc0498b751ad8ebea1083975c8346e1 100755 --- a/install_38.sh +++ b/install_38.sh @@ -10,9 +10,10 @@ bash pull_submodules.sh echo "Installing mamba" conda install mamba -n base -c conda-forge echo "Creating conda environment" -mamba env create python=3.8 --file conda-environment_py38_cu11_ubuntu.yml +mamba env create -n work38 python=3.8 eval "$(conda shell.bash hook)" # make sure conda works in the shell script conda activate work38 +mamba env update -n work38 --file conda-environment_py38_cu11_ubuntu.yml echo "Installing GDL" pip install Cython==0.29 pip install -e .