neural network - How to programmatically generate deploy.txt for caffe in python

Question

I have written python code to programmatically generate a convolutional neural network (CNN) for training and validation .prototxt files in caffe. Below is my function:

def custom_net(lmdb, batch_size):

    # define your own net!
    n = caffe.NetSpec()

    # keep this data layer for all networks
    n.data, n.label = L.Data(batch_size=batch_size, backend=P.Data.LMDB, source=lmdb,
                             ntop=2, transform_param=dict(scale=1. / 255))

    n.conv1 = L.Convolution(n.data, kernel_size=6,
                            num_output=48, weight_filler=dict(type='xavier'))
    n.pool1 = L.Pooling(n.conv1, kernel_size=2, stride=2, pool=P.Pooling.MAX)

    n.conv2 = L.Convolution(n.pool1, kernel_size=5,
                            num_output=48, weight_filler=dict(type='xavier'))
    n.pool2 = L.Pooling(n.conv2, kernel_size=2, stride=2, pool=P.Pooling.MAX)

    n.conv3 = L.Convolution(n.pool2, kernel_size=4,
                            num_output=48, weight_filler=dict(type='xavier'))
    n.pool3 = L.Pooling(n.conv3, kernel_size=2, stride=2, pool=P.Pooling.MAX)

    n.conv4 = L.Convolution(n.pool3, kernel_size=2,
                            num_output=48, weight_filler=dict(type='xavier'))
    n.pool4 = L.Pooling(n.conv4, kernel_size=2, stride=2, pool=P.Pooling.MAX)

    n.fc1 = L.InnerProduct(n.pool4, num_output=50,
                           weight_filler=dict(type='xavier'))

    n.drop1 = L.Dropout(n.fc1, dropout_param=dict(dropout_ratio=0.5))

    n.score = L.InnerProduct(n.drop1, num_output=2,
                             weight_filler=dict(type='xavier'))

    # keep this loss layer for all networks
    n.loss = L.SoftmaxWithLoss(n.score, n.label)

    return n.to_proto()

with open('net_train.prototxt', 'w') as f:
    f.write(str(custom_net(train_lmdb_path, train_batch_size)))

with open('net_test.prototxt', 'w') as f:
    f.write(str(custom_net(test_lmdb_path, test_batch_size)))

Is there a way to similarly generate deploy.prototxt for testing on unseen data that is not in an lmdb file? If so, i would really appreciate it if someone can point me to a reference.

Answer 1

Quite simply:

from caffe import layers as L, params as P
def custom_net(lmdb, batch_size):
    # define your own net!
    n = caffe.NetSpec()

    if lmdb is None: # "deploy" flavor
        # assuming your data is of shape 3x224x224
        n.data = L.Input(input_param={'shape':{'dim':[1,3,224,224]}})
    else:
        # keep this data layer for all networks
        n.data, n.label = L.Data(batch_size=batch_size, backend=P.Data.LMDB, source=lmdb,
                         ntop=2, transform_param=dict(scale=1. / 255))
    # the other layers common to all flavors: train/val/deploy...
    n.conv1 = L.Convolution(n.data, kernel_size=6,
                        num_output=48, weight_filler=dict(type='xavier'))
    n.pool1 = L.Pooling(n.conv1, kernel_size=2, stride=2, pool=P.Pooling.MAX)

    n.conv2 = L.Convolution(n.pool1, kernel_size=5,
                        num_output=48, weight_filler=dict(type='xavier'))
    n.pool2 = L.Pooling(n.conv2, kernel_size=2, stride=2, pool=P.Pooling.MAX)

    n.conv3 = L.Convolution(n.pool2, kernel_size=4,
                        num_output=48, weight_filler=dict(type='xavier'))
    n.pool3 = L.Pooling(n.conv3, kernel_size=2, stride=2, pool=P.Pooling.MAX)

    n.conv4 = L.Convolution(n.pool3, kernel_size=2,
                        num_output=48, weight_filler=dict(type='xavier'))
    n.pool4 = L.Pooling(n.conv4, kernel_size=2, stride=2, pool=P.Pooling.MAX)

    n.fc1 = L.InnerProduct(n.pool4, num_output=50,
                       weight_filler=dict(type='xavier'))
    # do you "drop" i deploy as well? up to you to decide...
    n.drop1 = L.Dropout(n.fc1, dropout_param=dict(dropout_ratio=0.5))
    n.score = L.InnerProduct(n.drop1, num_output=2,
                         weight_filler=dict(type='xavier'))

    if lmdb is None:
        n.prob = L.Softmax(n.score)
    else:
        # keep this loss layer for all networks apart from "Deploy"
        n.loss = L.SoftmaxWithLoss(n.score, n.label)

    return n.to_proto()

Now call the function:

with open('net_deploy.prototxt', 'w') as f:
    f.write(str(custom_net(None, None)))

As you can see there are two modifications to the prototxt (conditioned on lmdb being None):
The first, instead of "Data" layer, you have the declarative "Input" layer declaring only "data" and no "label".
The second change is the output layer: instead of a loss layer, you have a prediction layer (see, e.g., this answer).