Closed dingtiandu closed 6 years ago
Do you have the file now?
Hi,
we are not planning to release the training configuration file now but we might do it later on.
You can use the deploy.prototxt
and use it for training: just adjust the Batch Normalization configuration and add L2 loss function. More advanced loss functions can be implemented using caffe layers.
Thank you.
Can you share your solver.prototxt for training?Thanks.