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. 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. 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 ScanNet V2 dataset
Training on ScanNet doesnot require finetuning the backbone. Just freeze pretrained backbone and train the model. 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 ## Inference