search

TuSimple / TuSimple-DUC

Understanding Convolution for Semantic Segmentation
https://arxiv.org/abs/1702.08502
Apache License 2.0
610 stars 118 forks source link

How to set the custom learning rate. #24

Closed ZzzjzzZ closed 6 years ago

ZzzjzzZ commented 6 years ago

Hi, GrassSunFlower, I try to train the DUC network using the init.param, but the init.param do not contain the aspp weights, so I want to set the different learning rate of aspp to the front layers. I just want to know how to do this in MXNET, can you provide a eaxample. Thanks!

GrassSunFlower commented 6 years ago

You can implement your own optimizer to get this done.