martinkersner / train-DeepLab

Train DeepLab for Semantic Image Segmentation
MIT License
172 stars 76 forks source link

How to adapt the model of vgg to init model? #38

Open pkuCactus opened 6 years ago

pkuCactus commented 6 years ago

In VGG, the first connected layer is 4096 7x7 filters, how to adapt these param to 3x3 1024 or 4x4 4096? Is it just copy parameters in order and remove the others? Thanks a lot.