search

smallcorgi / Faster-RCNN_TF

Faster-RCNN in Tensorflow
MIT License
2.34k stars 1.12k forks source link

Fine-tuning #56

Open mpresecan opened 7 years ago

mpresecan commented 7 years ago

Hello I'm interested into fine-tunning pre-learned model. Do you have some recommendation where to start, and which layers I should train, and which of them I should fix. Is there any good tutorial on that? Thank you

snsie commented 7 years ago

I believe the home page example fine-tunes a pre-trained model. The info in the referenced issue is helpful for using your own dataset. https://github.com/smallcorgi/Faster-RCNN_TF/issues/3