lmb-freiburg / flownet2

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
https://lmb.informatik.uni-freiburg.de/Publications/2017/IMKDB17/
Other
1k stars 318 forks source link

how to use driving dataset to train this network? #19

Closed Lvhhhh closed 7 years ago

Lvhhhh commented 7 years ago

i have the dataset named driving including disparity and frames_cleanpass. how can i use it to train the network? how can i transfer the pfm to flo? and how can i create the list ? does it work if i have the list ? what the list looks like? thank you!

nikolausmayer commented 7 years ago

Hi,

  1. clone and compile this repo
  2. follow the README to download the models (which include training prototxt files)
  3. use these scripts to convert PFM to FLO and generate .list files
  4. use the convert_imageset_and_disparity tool (ships with this repo) to compile LMDB databases
  5. adjust the train prototxt file for a network of your choice (in ./models) and train
  6. ...
  7. profit! ;)

Best, Nikolaus