make_densenet.py 文件源码

def densenet(data_file, mode='train', batch_size=64, depth=40, first_output=16, growth_rate=12, dropout=0.2):
    data, label = L.Data(source=data_file, backend=P.Data.LMDB, batch_size=batch_size, ntop=2, 
              transform_param=dict(mean_file="/home/zl499/caffe/examples/cifar10/mean.binaryproto"))

    nchannels = first_output
    model = L.Convolution(data, kernel_size=3, stride=1, num_output=nchannels,
                        pad=1, bias_term=False, weight_filler=dict(type='msra'), bias_filler=dict(type='constant'))

    N = (depth-4)/3
    for i in range(N):
        model = add_layer(model, growth_rate, dropout)
        nchannels += growth_rate
    model = transition(model, nchannels, dropout)

    for i in range(N):
        model = add_layer(model, growth_rate, dropout)
        nchannels += growth_rate
    model = transition(model, nchannels, dropout)

    for i in range(N):
        model = add_layer(model, growth_rate, dropout)
        nchannels += growth_rate


    model = L.BatchNorm(model, in_place=False, param=[dict(lr_mult=0, decay_mult=0), dict(lr_mult=0, decay_mult=0), dict(lr_mult=0, decay_mult=0)])
    model = L.Scale(model, bias_term=True, in_place=True, filler=dict(value=1), bias_filler=dict(value=0))
    model = L.ReLU(model, in_place=True)
    model = L.Pooling(model, pool=P.Pooling.AVE, global_pooling=True)
    model = L.InnerProduct(model, num_output=10, bias_term=True, weight_filler=dict(type='xavier'), bias_filler=dict(type='constant'))
    loss = L.SoftmaxWithLoss(model, label)
    accuracy = L.Accuracy(model, label)
    return to_proto(loss, accuracy)