Skip to content

Latest commit

 

History

History

DPT

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
dpt
dpt
 
 
util
util
 
 
README.md
README.md
 
 
requirements.txt
requirements.txt
 
 
run_monodepth.py
run_monodepth.py
 
 

README.md

Benchamrk on paper Vision Transformers for Dense Prediction

  1. Download InSpaceType eval set. Install the requiremens.txt by '''pip install -r requirements.txt'''

  2. Download pretrained model 'dpt_hybrid_nyu-2ce69ec7.pt' from Official Link and put it under the folder 'weights'

python run_monodepth.py -t dpt_hybrid_nyu -i ../InSpaceType

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.