10-08-2018 08:10 AM
I try to compile classic SSD+VGG16 with DNNDK 2.06 beta. The slides and also the User-Guide claim to have "One-click compilation support" for SSD and VGG16.
However when I try to compile it I get:
[DNNC][Error] Unrecognized layer type [Normalize], Maybe you can delete it in deploy.prototxt and try again.
Is it planned to add support for the Normalize-Layer in future releases? Or is there some kind of replacement?
10-17-2018 08:01 PM
We made some modification with the original caffe-trained SSD network as follows,
a) Change the normalize layer to BatchNorm + Scale in the train.prototxt and test.prototxt, then retraining or finetune.
b) Remove the MultiBoxLoss layer in train.prototxt before Decent.
c) For the convenience of accuracy test, train.protxt and test.prototxt are merged to train_test.prototxt.
- Copy train.prototxt to train_test.prototxt
- Copy & paste the first layer of test.prototxt (AnnonateData layer) after the data layer of train_test.prototxt
- Copy & paste the last 5 layers starting from mbox_conf_reshape layer from test.prototxt to the end of train_test.prototxt,
then add the following parameter in these layers,
I hope this answers your question.