Question

我想将一个模型（f）的输出提供给另一个模型（c）。以下代码可以使用

features_ = sess.run(f.features, feed_dict={x:x_, y:y_, dropout:1.0, training:False})

sess.run(c.optimize, feed_dict={x:x_, y:y_, features:features_, dropout:1.0, training:False})

c只需要features_和y_。它不需要x_。但是，如果我尝试删除x_作为输入，即

feed_dict={y:y_, features:features_}

我收到以下错误：

InvalidArgumentError（参见上面的回溯）：你必须为占位符张量'占位符'提供一个值，其中dtype为float和shape [？，28,28,1] [[Node：Placeholder = Placeholderdtype = DT_FLOAT，shape = [？，28,28,1]，_ device =“/ job：localhost / replica：0 / task：0 / device：CPU：0”]]

这有什么理由吗？ features_是一个numpy ndarray，所以它似乎不是张量类型或类似的东西。

以下是f：

的代码

class ConvModelSmall(object):
    def __init__(self, x, y, settings, num_chan, num_features, lr, reg, dropout, training, scope):
        """ init the model with hyper-parameters etc """
        self.x = x
        self.y = y
        self.dropout = dropout
        self.training = training

        initializer = tf.contrib.layers.xavier_initializer(uniform=False)
        self.weights = get_parameters(scope=scope, initializer=initializer, dims)
        self.biases = get_parameters(scope=scope, initializer=initializer, dims)

        self.features = self.feature_model()
        self.acc = settings.acc(self.features, self.y)
        self.loss = settings.loss(self.features, self.y) + reg * reg_loss_fn(self.weights)
        update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
        with tf.control_dependencies(update_ops):
            self.optimize = tf.train.AdagradOptimizer(lr).minimize(self.loss)

    def feature_model(self):
        conv1 = conv2d('conv1', self.x, self.weights['wc1'], self.biases['bc1'], 2, self.training, self.dropout)
        conv2 = conv2d('conv2', conv1, self.weights['wc2'], self.biases['bc2'], 2, self.training, self.dropout)
        conv3 = conv2d('conv3', conv2, self.weights['wc3'], self.biases['bc3'], 2, self.training, self.dropout)

        dense1_reshape = tf.reshape(conv3, [-1, self.weights['wd1'].get_shape().as_list()[0]])
        dense1 = fc_batch_relu(dense1_reshape, self.weights['wd1'], self.biases['bd1'], self.training, self.dropout)
        dense2 = fc_batch_relu(dense1, self.weights['wd2'], self.biases['bd2'], self.training, self.dropout)

        out = tf.matmul(dense2, self.weights['wout']) + self.biases['bout']
        return out

以下是c：

的代码

class LinearClassifier(object):
    def __init__(self, features, y, training, num_features, num_classes, lr, reg, scope=""):
        self.features = features
        self.y = y
        self.num_features = num_features
        self.num_classes = num_classes

        initializer = tf.contrib.layers.xavier_initializer(uniform=False)
        self.W = get_scope_variable(scope=scope, var="W", shape=[num_features, num_classes], initializer=initializer)
        self.b = get_scope_variable(scope=scope, var="b", shape=[num_classes], initializer=initializer)

        scores = tf.matmul(tf.layers.batch_normalization(self.features, training=training), self.W) + self.b
        self.loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(labels=self.y, logits=scores)) + reg * tf.nn.l2_loss(self.W)
        update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
        with tf.control_dependencies(update_ops):
            self.optimize = tf.train.GradientDescentOptimizer(lr).minimize(self.loss)

Answer 1

魔鬼可能在这些方面：

    update_ops = tf.get_collection( tf.GraphKeys.UPDATE_OPS )
    with tf.control_dependencies(update_ops):
        self.optimize = tf.train.GradientDescentOptimizer( lr ).minimize( self.loss )

当您定义c时，f已定义，因此当您说update_ops = tf.get_collection( tf.GraphKeys.UPDATE_OPS )时，它会收集所有当前图表中的更新操作。这将包括与其中f，x相关的操作。

然后with tf.control_dependencies(update_ops):表示＆＃34;只有在所有update_ops被执行后，您才应执行以下，包括给x赋值。但是x没有价值，而且错误发生了。

要解决这个问题，您可以将两个网络分成两个不同的tf.Graph，或者，当您获得update_ops时，您可以更轻松地按照{{3}中的范围对其进行过滤}} 方法。要实现这一点，您应该将tf.get_collection()添加到您的网络类ConvModelSmall和LinearClassifier。

提供从一个模型到另一个模型的输出

1 个答案: