MD. Nazmul Kibria - 1 year ago 139

C++ Question

I need to update a caffe model from an existing caffe model where I will drop last two layers. It is needed to reduce caffe model size so that it would be easier and lesser size to deploy. Say my existing caffe model is **A1.caffemodel** which has ** 5 convolution layers** and

I appreciate your all valuable suggestions and helpful code snippet.

I have implemented according to below accepted answer in c++, I felt it needs to be shared:

`Net<float> caffe_net("B.prototxt", caffe::TEST);`

caffe_net.CopyTrainedLayersFrom("A.caffemodel");

caffe::NetParameter net_param;

caffe_net.ToProto(&net_param);

caffe::WriteProtoToBinaryFile(net_param, "B.caffemodel");

Answer Source

Fully connected layers can indeed be very heavy. Please look at section "3.1 Truncated SVD for faster detection" at *Girshick, R* **Fast-RCNN** ICCV 2015 describing how to use SVD trick to *significalntly* reduce the burden of fully connected layers. Hence, you can replace your three fully connected layers with 6 very thin layers.

Steps to go from model `A`

to `B`

:

Create

`B.prototxt`

that has the 5 convolution layers**with the same**as`"name"`

s`A`

.Give the single fully connected layer in

`B`

a new`"name"`

that does not exist in`A`

.in python

`import caffe B = caffe.Net('/path/to/B.prototxt', '/path/to/weights_A.caffemodel', caffe.TEST) B.save('/path/to/weights_B.caffemodel')`

Now you have weights for

`B`

that are the same as the weights of`A`

for all convolutional layers and**random**for the new single fully connected layer.fine tune model

`B`

starting from`'/path/to/weights_B.caffemodel'`

to learn the weights for the new single fully connected layer.