feat: add local paths to downloads since links are drive.google.com/*

This commit is contained in:
Laurent FAINSIN 2023-04-06 09:48:08 +02:00
parent e10fd5a3eb
commit c196f8d200
2 changed files with 5 additions and 2 deletions

3
.gitignore vendored
View file

@ -8,3 +8,6 @@ __pycache__
*.npz
eval_model
eval_data
ShapeNetCore.v2.PC15k*
checkpoints

View file

@ -30,7 +30,7 @@ The code was tested on Unbuntu with Titan RTX.
## Data
For generation, we use ShapeNet point cloud, which can be downloaded [here](https://github.com/stevenygd/PointFlow).
For generation, we use ShapeNet point cloud, which can be downloaded [here](https://github.com/stevenygd/PointFlow). Or at `/data/users/lfainsin/PVD/ShapeNetCore.v2.PC15k.zip`.
For completion, we use ShapeNet rendering provided by [GenRe](https://github.com/xiumingzhang/GenRe-ShapeHD).
We provide script `convert_cam_params.py` to process the provided data.
@ -43,7 +43,7 @@ $ python convert_cam_params.py --dataroot DATA_DIR --mitsuba_xml_root XML_DIR
which will create `..._cam_params.npz` in each provided data folder for each view.
## Pretrained models
Pretrained models can be downloaded [here](https://drive.google.com/drive/folders/1Q7aSaTr6lqmo8qx80nIm1j28mOHAHGiM?usp=sharing).
Pretrained models can be downloaded [here](https://drive.google.com/drive/folders/1Q7aSaTr6lqmo8qx80nIm1j28mOHAHGiM?usp=sharing). Or at `/data/users/lfainsin/PVD/checkpoints`.
## Training: