added basic download script (#410)

* basic script to download dataset

* update docs

.gitignore

@@ -12,6 +12,7 @@ build/
 develop-eggs/
 dist/
 downloads/
+!scripts/downloads/
 eggs/
 .eggs/
 lib/
@@ -185,4 +186,4 @@ node_modules/
 scripts/colmap2nerf.py
 bash/
 nerfactory/ngp_pl/
-cache/
+cache/

README.md

@@ -111,7 +111,13 @@ pytest tests
 
 #### 2. Getting the data
 
-Download the original [NeRF dataset](https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1) and unfold it in the following format. This is for the blender dataset type. We support the major datasets and allow users to create their own dataset, described in detail [here](https://plenoptix-nerfactory.readthedocs-hosted.com/en/latest/tutorials/data/index.html).
+Download the original NeRF Blender dataset. We support the major datasets and allow users to create their own dataset, described in detail [here](https://plenoptix-nerfactory.readthedocs-hosted.com/en/latest/tutorials/data/index.html).
+
+```
+python scripts/downloads/download_data.py --dataset=blender
+```
+
+Use `--help` to view all currently available datasets. The resulting script should download and unpack the dataset as follows:
 
 ```
 |─ nerfactory/

docs/tutorials/quickstart.md

@@ -48,7 +48,13 @@ pip install git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/to
 
 # Downloading data
 
-Download the original [NeRF dataset](https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1) and unfold it in the following format. This is for the blender dataset type. We support the major datasets and allow users to create their own dataset, described in detail [here](data/creating_dataset.md).
+Download the original NeRF Blender dataset. We support the major datasets and allow users to create their own dataset, described in detail [here](https://plenoptix-nerfactory.readthedocs-hosted.com/en/latest/tutorials/data/index.html).
+
+```
+python scripts/downloads/download_data.py --dataset=blender
+```
+
+Use `--help` to view all currently available datasets. The resulting script should download and unpack the dataset as follows:
 
 ```
 |─ nerfactory/

pyproject.toml

@@ -19,6 +19,7 @@ dependencies = [
     "av==9.2.0",
     "black[jupyter]==22.3.0",
     "dcargs>=0.3.1",
+    "gdown==4.5.1",
     "ninja==1.10.2.3",
     "functorch==0.2.1",
     "h5py>=2.9.0",

scripts/downloads/download_data.py

@@ -0,0 +1,77 @@
+"""Download datasets"""
+import zipfile
+from pathlib import Path
+from typing import Literal
+
+import dcargs
+import gdown
+
+
+def download_friends():
+    """Script ported from: https://github.com/ethanweber/sitcoms3D/blob/master/download_data.py"""
+    data_filename_to_file_id = [
+        ("./data/human_data.zip", "1zk12qxnZbReKqdvy-JYp1jQn2QA3oJzz"),
+        ("./data/human_pairs.zip", "1927rnmJ3mWcjsj0afqawSto2IK2lLwmA"),
+        ("./data/sparse_reconstruction_and_nerf_data.zip", "1RmwDUAp1T4RkwZg1S_7L9JAViWtBZfAG"),
+    ]
+
+    disk_data_filename_to_file_id = [  # pylint: disable=unused-variable
+        ("./data/sparse_reconstruction_and_nerf_data/ELR-apartment-disk.zip", "1YcTwMv5PP0uqXYdN-Lp8k0WnXUdHBXrY"),
+        ("./data/sparse_reconstruction_and_nerf_data/Frasier-apartment-disk.zip", "1vPqplDv5rrFu5LrxTHbET0FiePTGi8zE"),
+        (
+            "./data/sparse_reconstruction_and_nerf_data/Friends-monica_apartment-disk.zip",
+            "1yNpU4M44gIuWEaC5tSAOKy-A6KX8wTm8",
+        ),
+        (
+            "./data/sparse_reconstruction_and_nerf_data/HIMYM-red_apartment-disk.zip",
+            "1m76i46YYlpDKvlx-Jn7qDDAvkOVVVmqF",
+        ),
+        (
+            "./data/sparse_reconstruction_and_nerf_data/Seinfeld-jerry_living_room-disk.zip",
+            "1YFoV3Gd9asKsRarZvzRTYtri1755rBPx",
+        ),
+        ("./data/sparse_reconstruction_and_nerf_data/TAAHM-kitchen-disk.zip", "1QpF8kVGfgkqm_cDY5sY_E82BT8VOWL38"),
+        (
+            "./data/sparse_reconstruction_and_nerf_data/TBBT-big_living_room-disk.zip",
+            "175BjkpxMAOt75ZVIjYpArxWpO8uRexgJ",
+        ),
+    ]
+
+    # !!! Large files !!! Only uncomment if you need the disk correspondences.
+    # data_filename_to_file_id += disk_data_filename_to_file_id
+
+    for data_filename, file_id in data_filename_to_file_id:
+        # Download the files
+        url = f"https://drive.google.com/uc?id={file_id}"
+        gdown.download(url, output=data_filename, quiet=False)
+        with zipfile.ZipFile(data_filename, "r") as zip_ref:
+            zip_ref.extractall(data_filename.replace(".zip", "").replace("-disk", ""))
+        Path(data_filename).unlink(missing_ok=True)
+
+
+def download_blender():
+    """Download blender dataset and format accordingly"""
+    url = "https://drive.google.com/uc?id=18JxhpWD-4ZmuFKLzKlAw-w5PpzZxXOcG"
+    download_path = Path("data/blender_data.zip")
+    gdown.download(url, output=str(download_path), quiet=False)
+    with zipfile.ZipFile(download_path, "r") as zip_ref:
+        zip_ref.extractall("data/")
+    unzip_path = Path("data/nerf_synthetic")
+    final_path = Path("data/blender")
+    unzip_path.rename(final_path)
+    download_path.unlink(missing_ok=True)
+
+
+def main(dataset: Literal["blender", "friends"]):
+    """Main download script to download all data"""
+    save_dir = Path("data/")
+    save_dir.mkdir(parents=True, exist_ok=True)
+
+    if dataset == "blender":
+        download_blender()
+    if dataset == "friends":
+        download_friends()
+
+
+if __name__ == "__main__":
+    dcargs.cli(main)