search

marcellacornia / mlnet

A Deep Multi-Level Network for Saliency Prediction. ICPR 2016
MIT License
94 stars 37 forks source link

about fine-tune on MIT1003 #14

Closed ArchWing closed 6 years ago

ArchWing commented 6 years ago

Hi @marcellacornia Can you tell me more details about fine tuning on MIT1003?Such as learning rate config etc... Thank you.

marcellacornia commented 6 years ago

Hi @ArchWing, starting from the model trained on SALICON, we finetuned the network using 900 randomly selected training images and 103 validation images. The network configuration and the other parameters are the same used to train the network on the SALICON dataset.

Since images from MIT1003 dataset have different sizes, we decided to zero-pad them to fit a 4 : 3 aspect ratio.

ArchWing commented 6 years ago

@marcellacornia Thank you very much! Yeah, I see the size config is 640480, but because of the limit of gpu capacity, I change it to 426 320.