Safran/PointMLP
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

update requirements

Browse source
This commit is contained in:
Xu Ma 2022-04-25 01:38:08 -04:00
parent b9ed9778f2
commit 07195fec30
2 changed files with 15 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
README.md
View file

@ -89,7 +89,7 @@ pip install pointnet2_ops_lib/.
By default, it will create a folder named "checkpoints/{modelName}-{msg}-{randomseed}", which includes args.txt, best_checkpoint.pth, last_checkpoint.pth, log.txt, out.txt. By default, it will create a folder named "checkpoints/{modelName}-{msg}-{randomseed}", which includes args.txt, best_checkpoint.pth, last_checkpoint.pth, log.txt, out.txt.
```bash ```bash
cd pointMLP-pytorch/classification_ModelNet40 cd classification_ModelNet40
# train pointMLP # train pointMLP
python main.py --model pointMLP python main.py --model pointMLP
# train pointMLP-elite # train pointMLP-elite
@ -111,6 +111,7 @@ The dataset will be automatically downloaded
- Train pointMLP/pointMLPElite - Train pointMLP/pointMLPElite
```bash ```bash
cd classification_ScanObjectNN
# train pointMLP # train pointMLP
python main.py --model pointMLP python main.py --model pointMLP
# train pointMLP-elite # train pointMLP-elite
@ -124,7 +125,7 @@ By default, it will create a fold named "checkpoints/{modelName}-{msg}-{randomse
- Make data folder and download the dataset - Make data folder and download the dataset
```bash ```bash
cd pointMLP-pytorch/part_segmentation cd part_segmentation
mkdir data mkdir data
cd data cd data
wget https://shapenet.cs.stanford.edu/media/shapenetcore_partanno_segmentation_benchmark_v0_normal.zip --no-check-certificate wget https://shapenet.cs.stanford.edu/media/shapenetcore_partanno_segmentation_benchmark_v0_normal.zip --no-check-certificate

25
requirements.txt
View file

@ -1,13 +1,12 @@
cudatoolkit=10.2.89 torch
cycler=0.10.0 torchvision
einops=0.3.0 cudatoolkit
h5py=3.2.1 cycler
matplotlib=3.4.2 einops
numpy=1.20.2 h5py
numpy-base=1.20.2 matplotlib==3.4.2
pytorch=1.8.1 pytorch
pyyaml=5.4.1 pyyaml==5.4.1
scikit-learn=0.24.2 scikit-learn==0.24.2
scipy=1.6.3 scipy
torchvision=0.9.1 tqdm
tqdm=4.61.1