PROSAGA码农传奇-深度学习-tensorflow feature

<div class =“post-text”itemprop =“text”>
  <P>
    首先，您需要生产批次。有关详细信息，请参阅
    <a href="https://www.tensorflow.org/guide/datasets" rel="nofollow noreferrer">
      https://www.tensorflow.org/guide/datasets
    </A>
  </p>
   <pre>
    <code>
      ...
dataset = tf.data.Dataset.from_tensor_slices((features, labels))
dataset = dataset.batch(size)
  return dataset

</code>
  </pre>
  <P>
    然后重塑你的形象并投射到
     <code>
      float
    </code>
    。 -1表示batch_size，它将在训练期间被替换。根据提供的数据类型，将float标记为float是可选的。
  </p>
   <pre>
    <code>
          net = tf.cast(tf.reshape(features, [-1, 28*28]), tf.float32)
    labels = tf.cast(labels, tf.int64)
    net = tf.layers.dense(net, 10, tf.nn.relu)
    legits = tf.layers.dense(net, 10, activation=None)
    predicted_classes = tf.arg_max(legits, 1)
    if mode == tf.estimator.ModeKeys.PREDICT:
        predictions = {
            'class_ids': predicted_classes,
            'probabilities': tf.nn.softmax(legits),
            'logits': legits
        }
        return tf.estimator.EstimatorSpec(mode, predictions=predictions)

loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=legits)

if mode == tf.estimator.ModeKeys.EVAL:
        return tf.estimator.EstimatorSpec(mode, loss=loss)

optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.1)
    train_op = optimizer.minimize(loss, global_step=tf.train.get_global_step())
    return tf.estimator.EstimatorSpec(mode, loss=loss, train_op=train_op)

classifier = tf.estimator.Estimator(model_fn=my_model)

classifier.train(input_fn=lambda: input_train_fn(), steps=10)

</code>
  </pre>
</DIV>

tensorflow feature_column尝试重塑特征