search

torrvision / crfasrnn

This repository contains the source code for the semantic image segmentation method described in the ICCV 2015 paper: Conditional Random Fields as Recurrent Neural Networks. http://crfasrnn.torr.vision/
Other
1.34k stars 462 forks source link

Python Layer, Images Size #135

Closed mateovilla2 closed 7 years ago

mateovilla2 commented 7 years ago

Hello, I would like to ask 2 questions concerning the input layer :

CanI use a Python Layer( the Python layer provided in the FCN project) instead of the LMDB layer for the Input Images and Labels ? It doesn't give troubles when loading the .caffemodel? (obviously, modifying the net in the .prototxt file).

Can I use image of arbitrary size (max 512x512 pixels) , without padding ?

Thanks,

Mateo

bittnt commented 7 years ago

You can, but you are at your own risk doing so.