-
Download InSpaceType eval set. Install torch and torchivsion and packages: matplotlib, tqdm, pandas, opencv-python, tensorboardX
-
Download pretrained model 'bts_nyu_v2_pytorch_densenet161.zip' from Official Link and extract under 'model'
cd pytorch
python bts_test.py --dataset nyu --filenames_file ../train_test_inputs/split_files.txt --checkpoint_path models/bts_nyu_v2_pytorch_densenet161/model --max_depth 10 --encoder densenet161_bts --model_name bts_nyu_v2_pytorch_densenet161
The command generates report files for hierarchy (H0-H2). *-all means overall H0-H2 means level of hierarchy. H1_xx means scene space type number. See space_type_def.yml for space type number definition.