我想要的是,在加载网后,我将分解某些图层并保存新网。例如
Orignial net:
数据 - > conv1 - > conv2 - > fc1 - > fc2 - > SOFTMAX;
新网:
数据 - > conv1_1 - > conv1_2 - > conv2_1 - > conv2_2 - > fc1 - > fc2 - > SOFTMAX
因此,在此过程中,我陷入了以下情况:
1.如何在pycaffe
中新建一个具有指定图层参数的图层?
2.如何从现有图层(例如上面的fc1
和fc2
)复制图层参数?
我知道使用caffe::net_spec
,我们可以手动定义新网络。但caffe::net_spec
无法指定现有图层(例如:fc1
)。
答案 0 :(得分:10)
我没有看到如何使用net_spec加载以前的网络,但你总是可以直接使用protobuf对象。 (我以您的网络结构为例)
import caffe.proto.caffe_pb2 as caffe_pb2
import google.protobuf as pb
from caffe import layers as L
net = caffe_pb2.NetParameter()
with open('net.prototxt', 'r') as f:
pb.text_format.Merge(f.read(), net)
#example of modifing the network:
net.layer[1].name = 'conv1_1'
net.layer[1].top[0] = 'conv1_1'
net.layer[2].name = 'conv1_2'
net.layer[2].top[0] = 'conv1_2'
net.layer[2].bottom[0] = 'conv1_1'
net.layer[3].bottom[0] = 'conv2_2'
#example of adding new layers (using net_spec):
conv2_1 = net.layer.add()
conv2_1.CopyFrom(L.Convolution(kernel_size=7, stride=1, num_output=48, pad=0).to_proto().layer[0])
conv2_1.name = 'conv2_1'
conv2_1.top[0] = 'conv2_1'
conv2_1.bottom.add('conv1_2')
conv2_2 = net.layer.add()
conv2_2.CopyFrom(L.Convolution(kernel_size=7, stride=1, num_output=48, pad=0).to_proto().layer[0])
conv2_2.name = 'conv2_2'
conv2_2.top[0] = 'conv2_2'
conv2_2.bottom.add('conv2_1')
# then write back out:
with open('net2.prototxt, 'w') as f:
f.write(pb.text_format.MessageToString(net))