search

bonlime / keras-deeplab-v3-plus

Keras implementation of Deeplab v3+ with pretrained weights
MIT License
1.36k stars 428 forks source link

Edited "how to train this model" and "known issues" #78

Closed kelvin2468 closed 5 years ago

kelvin2468 commented 5 years ago

Revisions: -Useful parameters can be found in the original repository. Important notes:

  1. This model doesn’t provide default weight decay, user needs to add it themselves
  2. Due to huge memory use with OS=8, Xception backbone should be trained with OS=16 and only inferenced with OS=8.
  3. User can freeze feature extractor for Xception backbone (first 356 layers) and only fine-tune decoder. Right now (March 2019), there is a problem with finetuning Keras models with BN. You can read more about it here. Known issues This model can be retrained check this notebook. Finetuning is tricky and difficult because of the confusion between training and trainable in Keras. See this issue for a discussion and possible alternatives.

updated #77

bonlime commented 5 years ago

@kelvin2468
Thx for pull request!