MyTest.py 文件源码

def customNet(lmdb,batch_size):
    #define Lenet
    n = caffe.NetSpec()

    n.data, n.label = L.Data(batch_size=batch_size, backend=P.Data.LMDB, source=lmdb, transform_param=dict(scale=1./255),ntop=2)

    n.conv1 = L.Convolution(n.data, kernel_size=3, num_output=20, weight_filler=dict(type='xavier'))
    n.bn1 = L.BatchNorm(n.conv1,in_place=True)    
    n.scale1 = L.Scale(n.bn1,bias_term=True,bias_filler=dict(value=0),filler=dict(value=1))    
    n.conv2 = L.Convolution(n.scale1, kernel_size=3,stride=2, num_output=20, weight_filler=dict(type='xavier'))
    n.bn2 = L.BatchNorm(n.conv2,in_place=True)        
    n.scale2 = L.Scale(n.bn2,bias_term=True,bias_filler=dict(value=0),filler=dict(value=1))        
#    n.pool1 = L.Pooling(n.scale2, kernel_size=2, stride=2, pool=P.Pooling.MAX)
    n.conv3 = L.Convolution(n.scale2, kernel_size=3, num_output=50, weight_filler = dict(type='xavier'))
    n.bn3 = L.BatchNorm(n.conv3,in_place=True)        
    n.scale3 = L.Scale(n.bn3,bias_term=True,bias_filler=dict(value=0),filler=dict(value=1))        
    n.conv4 = L.Convolution(n.scale3, kernel_size=3, stride=2,num_output=50, weight_filler=dict(type='xavier'))
    n.bn4 = L.BatchNorm(n.conv4,in_place=True)        
    n.scale4 = L.Scale(n.bn4,bias_term=True,bias_filler=dict(value=0),filler=dict(value=1))    

#    n.pool2 = L.Pooling(n.scale4, kernel_size=2, stride=2, pool=P.Pooling.MAX)
    n.fc1 = L.InnerProduct(n.scale4, num_output=500, weight_filler=dict(type='xavier'))
    n.relu1 = L.ReLU(n.fc1, in_place=True)
    n.fc2 = L.InnerProduct(n.relu1, num_output=100, weight_filler=dict(type='xavier'))
    n.relu2 = L.ReLU(n.fc2, in_place=True)
    n.score = L.InnerProduct(n.relu2,num_output=10, weight_filler=dict(type='xavier'))
    n.loss = L.SoftmaxWithLoss(n.score, n.label)

    return n.to_proto()