search

yunxiaoshi / Neural-IMage-Assessment

A PyTorch Implementation of Neural IMage Assessment
Other
526 stars 95 forks source link

Learning Rate Setting #16

Open mr-Mojo opened 4 years ago

mr-Mojo commented 4 years ago

Hi, I am experimenting with the NIMA implementation for a scientfic project! In your Readme, you say that "The learning rate setting differs from the original paper. I can't seem to get the model to converge with momentum SGD using an lr of 3e-7 for the conv base and 3e-6 for the dense block.". Which settings did you use? The defaults in argparser are set to the 3e-7, 3e-6, so that's why I was wondering!

Thank you :)

yunxiaoshi commented 4 years ago

0.005 for the dense block and 0.0005 for the conv base gives you a reasonable result. But I suspect it is not optimal, maybe do a grid/random search