From 4e5112d91cf9808a5c01fc43809344c2c7aae746 Mon Sep 17 00:00:00 2001
From: caxapexac <caxapexac@gmail.com>
Date: Wed, 4 Mar 2020 16:26:37 +0300
Subject: [PATCH] Installation guide

Added support for multiple download_trained_model.sh launch
Added installation guide
---
 .gitignore                        |  1 +
 README.md                         | 30 +++++++++++++++++++++++++++++-
 scripts/download_trained_model.sh |  2 +-
 3 files changed, 31 insertions(+), 2 deletions(-)
 create mode 100644 .gitignore

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 00000000..e708e040
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+checkpoints/*
diff --git a/README.md b/README.md
index 54a16fea..12b5b900 100755
--- a/README.md
+++ b/README.md
@@ -33,14 +33,42 @@ This codebase provides:
 - PIL
 - skimage
 - tqdm
+- numpy
+- cv2
 
 for training and data generation
 - [trimesh](https://trimsh.org/) with [pyembree](https://github.com/scopatz/pyembree)
-- cv2
 - [pyexr](https://github.com/tvogels/pyexr)
 - PyOpenGL
 - freeglut (use `sudo apt-get install freeglut3-dev` for ubuntu users)
 
+## Windows demo installation instuction
+
+- Install [miniconda](https://docs.conda.io/en/latest/miniconda.html)
+- Add `conda` to PATH
+- Install [git bash](https://git-scm.com/downloads)
+- Launch `Git\bin\bash.exe`
+- `eval "$(conda shell.bash hook)"` then `conda activate my_env` because of [this](https://github.com/conda/conda-build/issues/3371)
+- Automatic `env create -f environment.yml` (look [this](https://github.com/conda/conda/issues/3417))
+- OR manually setup [environment](https://towardsdatascience.com/a-guide-to-conda-environments-bc6180fc533)
+    - `conda create —name pifu python` where `pifu` is name of your environment
+    - `conda activate`
+    - `conda install pytorch torchvision cudatoolkit=10.1 -c pytorch`
+    - `conda install pillow`
+    - `conda install scikit-image`
+    - `conda install tqdm`
+    - `conda install -c menpo opencv`
+- Download [wget.exe](https://eternallybored.org/misc/wget/)
+- Place it into `Git\mingw64\bin`
+- `sh ./scripts/download_trained_model.sh`
+- Remove background from your image ([this](https://www.remove.bg/), for example)
+- Create black-white mask .png
+- Replace original from sample_images/
+- Try it out - `sh ./scripts/test.sh`
+- Download [Meshlab](http://www.meshlab.net/) because of [this](https://github.com/shunsukesaito/PIFu/issues/1)
+- Open .obj file in Meshlab
+
+
 ## Demo
 Warning: The released model is trained with mostly upright standing scans with weak perspectie projection and the pitch angle of 0 degree. Reconstruction quality may degrade for images highly deviated from trainining data.
 1. run the following script to download the pretrained models from the following link and copy them under `./PIFu/checkpoints/`.
diff --git a/scripts/download_trained_model.sh b/scripts/download_trained_model.sh
index c86a2845..c652f2c6 100755
--- a/scripts/download_trained_model.sh
+++ b/scripts/download_trained_model.sh
@@ -1,6 +1,6 @@
 set -ex
 
-mkdir checkpoints
+mkdir -p checkpoints
 cd checkpoints
 wget "https://drive.google.com/uc?export=download&id=1zEmVXG2VHy0MMzngcRshB4D8Sr_oLHsm" -O net_G
 wget "https://drive.google.com/uc?export=download&id=1V83B6GDIjYMfHdpg-KcCSAPgHxpafHgd" -O net_C