tensorflow - 如何在 Tensorflow 中拥有可变数量的隐藏层？

Question

假设我们想尝试排序隐藏层数量及其大小。我们可以在 Tensorflow 中做什么？

请考虑以下示例以使其清楚:

# Create a  Neural Network Layer

def fc_layer(input, size_in, size_out):
        w = tf.Variable(tf.truncated_normal([None, size_in, size_out]), name="W")
        b = tf.Variable(tf.constant(0.1, shape=[size_out]))
        act = tf.matmul(input, w) + b
        return act
n_hiddenlayers=3 #number of hidden layers
hidden_layer=tf.placeholder(tf.float32,[n_hiddenlayers, None, None])
#considering 4 as size of inputs and outputs of all layers
sizeInpOut=4
for i in range(n_hiddenlayers):
    hidden_layer(i,:,:)= tf.nn.sigmoid(fc_layer(X, sizeInpOut, sizeInpOut))

这会导致关于hidden_​​layer(i,:,:)= ...的错误换句话说，我需要张量的张量。

Answer 1

我只是使用一个列表来保存不同的图层，如下所示，似乎工作正常。

    # inputs
    x_size=2 # first layer nodes
    y_size=1 # final layer nodes
    h_size=[3,4,3] # variable length list of hidden layer nodes

    # set up input and output
    X = tf.placeholder(tf.float32, [None,x_size])
    y_true = tf.placeholder(tf.float32, [None,y_size])

    # set up parameters
    W = []
    b = []
    layer = []

    # first layer
    W.append(tf.Variable(tf.random_normal([x_size, h_size[0]], stddev=0.1)))
    b.append(tf.Variable(tf.zeros([h_size[0]])))

    # add hidden layers (variable number)
    for i in range(1,len(h_size)):
        W.append(tf.Variable(tf.random_normal([h_size[i-1], h_size[i]], stddev=0.1)))
        b.append(tf.Variable(tf.zeros([h_size[i]])))

    # add final layer
    W.append(tf.Variable(tf.random_normal([h_size[-1], y_size], stddev=0.1)))
    b.append(tf.Variable(tf.zeros([y_size])))

    # define model
    layer.append(tf.nn.relu(tf.matmul(X, W[0]) + b[0]))

    for i in range(1,len(h_size)):
        layer.append(tf.nn.relu(tf.matmul(layer[i-1], W[i]) + b[i]))

    if self.type_in == "classification":
        y_pred = tf.nn.sigmoid(tf.matmul(layer[-1], W[-1]) + b[-1])
        loss = tf.reduce_mean(-1. * ((y_true * tf.log(y_pred)) + ((1.-y_true) * tf.log(1.-y_pred))))
        correct_prediction = tf.equal(tf.round(y_pred), tf.round(y_true))
        metric = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
        metric_name = "accuracy"