how to fine-tune or retrain matchnet? about matchnet

[hanxf]

To train/fine-tune jointly, you can connect two FeatureNet to the MetricNet then implement an input layer that feeds batches to the two bottom layers of the FeatureNet. The FeatureNet layers can share parameters by having the same name in the "param" block. You can checkout Caffe's mnist siamese examples.

[LeonSCZ]

@hanxf ,i've been on this experiment for a long long time,and my loss was still about 0.69,how can i know the way you train this network?

[LeonSCZ]

@hanxf This is my net architecture and my solver file.Do I have any mistakes in my files?Thank you a lot
mnist_siamese_solver.txt
mnist_siamese_train_test.txt

[447425299]

@hanxf Thank for your sharing, i know how to share parameters as Caffe's mnist siamese examples, but how to connect the two Bottleneck layers to the FC layer. Thank a lot again.

[447425299]

@virusme Have you done the work? fine-tune the network?

[virusme]

@447425299 Apologies for a really late response. I have moved on since I posted this issue (as you can see it is over 3 years old). I cannot remember if I ended up fine tuning the network.