Closed hengck23 closed 7 years ago
Hi @hengck23,
We've updated BN layers only in the pre-training step. In Faster R-CNN training, BN layers work just like scale-bias layers with fixed params.
@sanghoon That is very helpful. Thanks!
@sanghoon
there is a new paper on batch norm for small batch size (as small as batch=4). This may help. https://arxiv.org/abs/1702.03275
Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models Sergey Ioffe (Submitted on 10 Feb 2017)
Hi,
The original faster RCNN train with batch size=1 or 2. But for BN (batch normalization) layer, we need sufficient statistic to correctly estimate the mean and variance parameters. How did you solve this problem?
Thank you very much.