Browse Source

update

master
yehua 1 month ago
parent
commit
4c8f242095
2 changed files with 35 additions and 7 deletions
  1. +26
    -7
      README.md
  2. +9
    -0
      pytorch/requirements-pytorch.txt

+ 26
- 7
README.md View File

@@ -27,34 +27,53 @@ Paper Citation:
11.results: test results by contributors

## environment
refer to PCGCv1-master/README.md and 'PCGCv1 explanation.docx'
### 1.pytorch
- ubuntu 18.04
- cuda V10.2.89
- python 3.6.9
- refer to pytorch/requirements-pytorch.txt

### 2.tensorlayer
- Ubuntu 18.04
- cuda 10.1.243
- python 3.7.6
- tensorflow-gpu 2.3.1
- tensorlayer3 1.2.0
- torch 1.8.1
- torchac 0.9.3
- refer to pytorch/requirements-pytorch.txt

## command
### 1.pytorch
> cd pytorch

training:
> python train.py

encode:
> python test.py compress --input=".../redandblack_vox10_1550.ply" --ckpt_dir=".../epoch_13_12599.pth" --batch_parallel=64
> python test.py compress --input=".../redandblack_vox10_1550.ply" --ckpt_dir="ckpts/epoch_13_13599_a6b3.pth" --batch_parallel=64

decode:
> python test.py decompress --input="compressed/longdress_vox10_1300" --ckpt_dir=".../epoch_13_12599.pth"
> python test.py decompress --input="compressed/longdress_vox10_1300" --ckpt_dir="ckpts/epoch_13_13599_a6b3.pth"

evaluate:
> python eval.py --input ".../longdress_vox10_1300.ply" --ckpt_dir=".../epoch_13_12599.pth"
> python eval.py --input ".../longdress_vox10_1300.ply" --ckpt_dir="ckpts/epoch_13_13599_a6b3.pth"

### 2.tensorlayer

> cd tensorlayer

training:
> python train.py

encode:
> python test.py compress --input=".../redandblack_vox10_1550.ply" --ckpt_dir=".../ epoch_18_18199.npz" --batch_parallel=4
> python test.py compress --input=".../redandblack_vox10_1550.ply" --ckpt_dir="ckpts/epoch_30_30349_a6b3.npz" --batch_parallel=4

decode:
> python test.py decompress --input="compressed/longdress_vox10_1300" --ckpt_dir=".../ epoch_18_18199.npz"
> python test.py decompress --input="compressed/longdress_vox10_1300" --ckpt_dir="ckpts/epoch_30_30349_a6b3.npz"

evaluate:
> python eval.py --input ".../longdress_vox10_1300.ply" --ckpt_dir=".../ epoch_18_18199.npz "
> python eval.py --input ".../longdress_vox10_1300.ply" --ckpt_dir="ckpts/epoch_30_30349_a6b3.npz"

## performance
We first caculate the BD-PSNR and BD-BR rate of PCGCv1 and GPCC trisoup over GPCC octree on many PCs, the result shows as below. We can see from the table, that for dense PC with bit width of 10 and 11, PCGCv1 gets better performance over octree and trisoup, while for sparse or vox12 PC, it gets worse. The main reason is that there is no PC data in training sets with similar distributions or geometry features.


+ 9
- 0
pytorch/requirements-pytorch.txt View File

@@ -0,0 +1,9 @@
h5py==2.10.0
matplotlib==3.1.1
numpy==1.17.2
open3d==0.11.2
pandas==0.24.2
pyntcloud==0.1.4
torch==1.8.1
torchac==0.9.3
tqdm==4.38.0

Loading…
Cancel
Save