diff --git a/README.md b/README.md index 5b32e29..e1f9c83 100644 --- a/README.md +++ b/README.md @@ -71,8 +71,13 @@ Our provided install method is based on Conda package and environment management conda env create --file environment.yml conda activate gaussian_splatting ``` +Note for Windows: if setup stops and you are prompted to set ```DISTUTILS_USE_SDK=1```, please complete the environment setup with: +```shell +SET DISTUTILS_USE_SDK=1 +conda env update --file environment.yml +``` -Note that downloading packages and creating a new environment with Conda can require a significant amount of disk space. By default, Conda will use the main system hard drive. You can avoid this by specifying a different package download location and an environment on a different drive: +Tip: Downloading packages and creating a new environment with Conda can require a significant amount of disk space. By default, Conda will use the main system hard drive. You can avoid this by specifying a different package download location and an environment on a different drive: ```shell conda config --add pkgs_dirs / diff --git a/SIBR_viewers_windows b/SIBR_viewers_windows index eb1b851..0a1620a 160000 --- a/SIBR_viewers_windows +++ b/SIBR_viewers_windows @@ -1 +1 @@ -Subproject commit eb1b8513ecc0cdb1dfbd9dae4e0fe64c9dcef2ab +Subproject commit 0a1620ace38f1d26e685312a533cc95064902c15 diff --git a/train.py b/train.py index 838a4eb..0e0c0c4 100644 --- a/train.py +++ b/train.py @@ -180,6 +180,8 @@ if __name__ == "__main__": parser.add_argument("--save_iterations", nargs="+", type=int, default=[7_000, 30_000]) parser.add_argument("--quiet", action="store_true") args = parser.parse_args(sys.argv[1:]) + args.save_iterations.append(args.iterations) + print("Optimizing " + args.model_path) # Initialize system state (RNG)