Decoder training in main_distill_mono.py

xy-guo / Learning-Monocular-Depth-by-Stereo

Learning Monocular Depth by Distilling Cross-domain Stereo Networks, ECCV18

https://arxiv.org/abs/1808.06586

MIT License

94 stars 8 forks source link

Decoder training in main_distill_mono.py #8

Closed kwea123 closed 5 years ago

kwea123 commented 5 years ago

https://github.com/xy-guo/Learning-Monocular-Depth-by-Stereo/blob/3547a9e6f081177114e997e5986b2b546cee6109/main_distill_mono.py#L104

Here you train the decoder only for the first epoch. Why?

xy-guo commented 5 years ago

Only the encoder is initialized with ImageNet pretrained weights, while the decoder is randomly initialized. I hope to train the randomly initialized decoder for one epoch first, then the whole network. I think this could produce more robust model.

kwea123 commented 5 years ago

Oh, I misunderstood that as "training the decoder only for the first epoch, and stop training it from the second epoch and on." Now it's clear and good.