Modifying pretraind Neural Network
显示 更早的评论
I plan to use a pretrained net such as alexnet, with input image of 227*227*5 . I exported the net to the Network Designer App. and changed the input and first convulution layers according to my requirements. I analyzed the archirecture and it seems perfect. Can I trust the new network to be a good starting point or I'm naive?
Thanks,
Shai
采纳的回答
Srivardhan Gadila
2020-4-8
1 个投票
Since the convolution2dLayer and imageInputLayer have been replaced, the output of the ImageInputLayer would be different now because initially for the zero-center nomalization the mean used was different and also the features extracted/output from the replaced convolution layer would be different and may not be useful. If you are training the network on the new dataset with image input size 227*227*5 then above all doesn't matter. Instead if you are using it for feature extraction & your data is very different from the original data, then the features extracted deeper in the network might be less useful for your task.
Here are few suggestions while retrianing:
- Try freezing the weights of the original layers by setting the WeightLearnRateFactor and BiasLearnRateFactor to zero for convolution2dLayer and the same WeightLearnRateFactor & BiasLearnRateFactor for the fullyConnectedLayer too.
- Or retrain the complete network without freezing weights of any particular layers.
更多回答（0 个）
类别
在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
