I would like to use an existing VGG16 model trained on imagenet and fine-tune it with a custom dataset for some other classes required by me.
Where can I find the caffemodel, train_val.prototxt and solver.prototxt for the same ?
To fine-tune it with the custom dataset, is the procedure same as
Fine Tuning of GoogLeNet Model
A guide to convert_imageset.cpp
?
However, I want to use the newly-trained weights of the VGG16 model to train a faster RCNN (py-faster-rcnn) https://github.com/rbgirshick/py-faster-rcnn on a custom dataset. For training faster RCNN on a custom dataset, I was planning on following the steps given here http://sgsai.blogspot.com/2016/02/training-faster-r-cnn-on-custom-dataset.html
Will the caffemodel generated from the VGG16 fine-tuning done earlier work here or some tweaks need to be done ?
