Closed amiltonwong closed 4 years ago
Hi, you have to specify a config file to build the model before loading the checkpoint:
python train.py [config file in configs/] --devices [gpu id] [other options]
Please run the following command,
python train.py configs/s3dis/pvcnn/area5.py --devices 0 --evaluate --configs.train.best_checkpoint_path /data/code11/pvcnn/trained_models/s3dis.pvcnn.area5.pth.tar
Hi, @synxlin ,
Thanks for your reply. I use the command your mentioned:
python train.py configs/s3dis/pvcnn/area5.py --devices 0 --evaluate --configs.train.best_checkpoint_path /data/code11/pvcnn/trained_models/s3dis.pvcnn.area5.pth.tar
. However, I got this error. It seems the error comes from c++ extention or Ninja package.
My system is pytorch 1.0 and Ninja-1.9.0 installed.
Any suggestion to solve this issue?
THX!
Hi, You need Pytorch >= 1.3. I will update the README.md.
Hi, authors,
After input the command
python train.py --devices 0 --evaluate --configs.train.best_checkpoint_path /data/code11/pvcnn/trained_models/s3dis.pvcnn.area5.pth.tar
, I got the following error :Is there something wrong with the command I used or something wrong with the relative import?
THX!