From 70f1a5199773163ea71313a4463b03d9d35a3812 Mon Sep 17 00:00:00 2001
From: Laurent COLBOIS <laurent.colbois@idiap.ch>
Date: Fri, 9 Jul 2021 10:01:25 +0200
Subject: [PATCH] Update README.rst
---
README.rst | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/README.rst b/README.rst
index b99efde..bba7407 100644
--- a/README.rst
+++ b/README.rst
@@ -86,6 +86,13 @@ This second step creates a `bin` folder containing in particular
How to run
----------
+TL;DR
+*****
+1. Setup preset paths using :code:`bob config set`
+2. Download model dependencies using :code:`./bin/download_models.py`
+3. If having access to Multi-PIE : project it in StyleGAN2 latent space (:code:`./bin/project_db.py`), then use it to compute latent directions (:code: `./bin/latent_analysis.py`). If not having access to Multi-PIE, you can use the provided `precomputed/latent_directions.pkl` as a starting point.
+4. Generate a synthetic database using the precomputed latent directions using :code:`./bin/generate_db.py`.
+
Download model dependencies
***************************
The database generation in this project relies on several preexisting pretrained models:
@@ -145,7 +152,7 @@ Run dataset projection
**********************
Database projection is performed by running the `./bin/project_db.py` script. Premade configuration files are available in the repository to
perform the projection of three subsets of interest of the Multipie database (image from the world group for the U, E and P protocol).
-StyleGAN2 only runs on GPU, therefore the projection should be made on a computation node with a GPU. Moreover, on the Idiap SGE grid, one can easily split the projection process
+StyleGAN2 **only runs on GPU**, therefore the projection should be made on a computation node with a GPU. Moreover, on the Idiap SGE grid, one can easily split the projection process
between several parallel jobs by submitting them through `jman`. By default (unless one uses the `--force` flag), images are not reprojected if their latent projection is already
present in the output folder, which enables to interrupt & restart projection in a series of sequential `sgpu` jobs.
One can run `./bin/project_db.py --help` to get more info on the required configuration values.
@@ -197,7 +204,7 @@ Here is an example when scaling synmultipie to 10k identities:
dependency=$(cat create_identities_job_id)
jman submit -n make_variations -q gpu -t 8 -x $dependency -s "PYTHONUNBUFFERED=1" -- ./bin/generate_db.py synmultipie -n 10000 --subtask populate-identities
-This first launches a single job generating all references. One this job finishes, 8 parallel jobs between which
+The first command launches a single job generating all references. One this job finishes, 8 parallel jobs between which
the identities are split to generate all variations.
Run benchmark experiments
--
GitLab