py-R-FCN Fine Tuning

How to fine tune your model? I don't have sufficient data to retrain your model from scratch.I want to fine tune your model on my data which has only two classes ?

Oct 31 '16 12:10 mzahran001

Please see this thread for layer specific changes: https://github.com/Orpine/py-R-FCN/issues/9 Note that this will not suffice if you are changing anchors as well. Let me know if you are doing that. To fine tune an existing model, you can replace the ResNet-<50/101>-model.caffemodel that you provide while following training steps.

Dec 07 '16 05:12 ravikantb

@ravikantb What are some heuristics for fine tuning the RFCN network when training on own dataset? E.g. on a moderate number of classes lower than PASCAL_VOC but where classes are harder than those on PASCAL_VOC (cars, ...)

Mar 16 '17 11:03 dantp-ai

@ I have already fined tune resnet101_rfcn_final.caffemodel model, it got 95% accuracy in training. But in demo_rfcn.py, I test my image, the predicted boxes were inaccurate. I do not know why?

Jul 20 '19 08:07 longzeyilang