search

nqanh / affordance-net

AffordanceNet - Multiclass Instance Segmentation Framework - ICRA 2018
Other
121 stars 54 forks source link

about pretrain model #11

Open chenmyzju opened 6 years ago

chenmyzju commented 6 years ago

Hi I found that I couldn't get a good model when I didn't use the pretrained model I couldn't detect anything when I didn't use the pretrained model . The same backbone network with VGG16 and after 50 thousand times iters.

so is it due to the hyperpameter ? when I change the backbone network with the PVAlite network , I also find this issue thank you

nqanh commented 6 years ago

Yes, pretrained model helps us to reduce the training time and also better initialization for the model parameters. If you don't use it, then I guess you will need to train for a very long time, 50K inters may not be enough.