vhad/SoftGroup
1
0
Fork 0
mirror of https://github.com/botastic/SoftGroup.git synced 2025-10-16 11:45:42 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Thang Vu 2022-04-16 19:03:35 +09:00 committed by GitHub
parent 3fe43242b1
commit f3188a9921
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -45,17 +45,17 @@ The default configs suppose training on 4 GPU. If you use smaller number of GPUs
First, finetune the pretrained HAIS point-wise prediction network (backbone) on S3DIS.
```
./tools/dist_train.sh config/softgroup_s3dis_backbone_fold5.yaml 4
./tools/dist_train.sh configs/softgroup_s3dis_backbone_fold5.yaml 4
```
Then, train model from frozen backbone.
```
./tools/dist_train.sh config/softgroup_s3dis_fold5.yaml 4
./tools/dist_train.sh configs/softgroup_s3dis_fold5.yaml 4
```
### Training ScanNet V2 dataset
Training on ScanNet doesnot require finetuning the backbone. Just freeze pretrained backbone and train the model.
```
./tools/dist_train.sh --config config/softgroup_scannet.yaml 4
./tools/dist_train.sh configs/softgroup_scannet.yaml 4
```
## Inference