search

0bserver07 / One-Hundred-Layers-Tiramisu

Keras Implementation of The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation by (Simon Jégou, Michal Drozdzal, David Vazquez, Adriana Romero, Yoshua Bengio)
https://arxiv.org/abs/1611.09326
MIT License
197 stars 54 forks source link

Fine Tuning ... #8

Open MyVanitar opened 7 years ago

MyVanitar commented 7 years ago

Hi,

How to fine-tune the model for a custom dataset with different number of classes?

Typically I should handle the pretrained model (I could not find the download link) and train the model with different number of classes on the custom dataset, but with the same format as original one.

csjfwang commented 7 years ago

Hi @VanitarNordic ,

Did you solve this problem? And i want to ask if you can train and test this FC-DenseNet?

Thank you !

MyVanitar commented 7 years ago

Sorry, No.