Activations of freezed layers are different between before/after training, why?
2 次查看(过去 30 天)
显示 更早的评论
I follow the example "transfer-learning-using-googlenet" where, the last 3 layers ('loss3-classifier','prob','output') are replaced with 3 new ones. Then I 'freeze' the first 141 layers (that is up to and including 'pool5-drop_7x7_s1'):
layers(1:141) = freezeWeights(layers(1:141));
lgraph = createLgraphUsingConnections(layers,connections);
Then I follow fine-tuning.
Since 'pool5-7x7_s1' is BEFORE 'pool5-drop_7x7_s1', I would expect that the following two vectors were the same:
b_orig= activations(net_orig, I, 'pool5-7x7_s1');
b_tune= activations(net_tune, I, 'pool5-7x7_s1');
but they aren't!... Any idea why?
p.s. I also tried the activation of several other layers BEFORE 'pool5-drop_7x7_s1', and I got different vectors.... 'I' is an image, 'net_orig=googlenet;', and 'net_tune' is the resulting net after tuning.
2 个评论
采纳的回答
Amanjit Dulai
2018-8-14
The vectors are different because when you fine tune on a new dataset, the average image in "imageInputLayer" is recalculated for your new dataset.
更多回答(0 个)
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!