search

sczhou / DAVANet

[CVPR 2019, Oral] DAVANet: Stereo Deblurring with View Aggregation
MIT License
137 stars 25 forks source link

Thanks for your work,I have some questions #1

Closed gittigxuy closed 5 years ago

gittigxuy commented 5 years ago

1)how could I train gopro dataset? 2)now,I am working with car card deblur,does your work is fit in my project? 3)how about the GPU memory usage?and the test speed in gopro dataset? Thanks

sczhou commented 5 years ago

1)how could I train gopro dataset? 2)now,I am working with car card deblur,does your work is fit in my project? 3)how about the GPU memory usage?and the test speed in gopro dataset? Thanks

  1. change the settings in config.py file: C.NETWORK.DEBLURNETARCH = 'DeblurNet' C.NETWORK.MODULE = 'deblurnet'
  2. and you need to change the IO codes for GOPRO dataset.

Best and thanks.

gittigxuy commented 5 years ago

how about your model inference speed,and GPU memory usage? and could you please update your code to support train gopro?