search

facebookarchive / fb.resnet.torch

Torch implementation of ResNet from http://arxiv.org/abs/1512.03385 and training scripts
Other
2.29k stars 664 forks source link

Fine-tuning model #155

Open bmsookim opened 7 years ago

bmsookim commented 7 years ago

Is fine-tuning the pretrained model with different learning rates for each step is possible?

For example, adapting 0.001 rate for the first convolution, 0.0001 for the second convolution, 0.00001 for the third convolution... etc.

RetrieverJo commented 7 years ago

You can set your own learning rate policy on "train.lua" script. At last of the script, you can modify "Trainer:learningRate" function.