【学习笔记】嵌入以及神经网络的保存和读取

我们之前用indicator的方式将数据multi-hot上，输出结果的shape为[batchsize,50]，我们能不能对维度再次压缩呢？

答案是可以的。这里我们将会运用embedding的方法。大体写法均没有动

import tensorflow as tf

def _parse_function(record):
    """Extracts features and labels.

    Args:
      record: File path to a TFRecord file
    Returns:
      A `tuple` `(labels, features)`:
        features: A dict of tensors representing the features
        labels: A tensor with the corresponding labels.
    """
    features = {
        "terms": tf.VarLenFeature(dtype=tf.string),  # terms are strings of varying lengths
        "labels": tf.FixedLenFeature(shape=[1], dtype=tf.float32)  # labels are 0 or 1
    }

    parsed_features = tf.parse_single_example(record, features)

    terms = parsed_features['terms'].values
    labels = parsed_features['labels']

    return {'terms': terms}, labels


def my_input_fn(input_filenames, num_epochs=None, shuffle=True):
    # Same code as above; create a dataset and map features and labels.
    ds = tf.data.TFRecordDataset(input_filenames)
    ds = ds.map(_parse_function)

    if shuffle:
        ds = ds.shuffle(10000)

    # Our feature data is variable-length, so we pad and batch
    # each field of the dataset structure to whatever size is necessary.
    ds = ds.padded_batch(25, ds.output_shapes)

    ds = ds.repeat(num_epochs)

    # Return the next batch of data.
    features, labels = ds.make_one_shot_iterator().get_next()
    return features, labels

def add_layer(inputs, input_size, output_size, activation_function=None):
    weights = tf.Variable(tf.random_normal([input_size, output_size], stddev=.1))
    biases = tf.Variable(tf.zeros([output_size]) + .1)
    wx_b = tf.matmul(inputs, weights) + biases
    if activation_function is None:
        outputs = wx_b
    else:
        outputs = activation_function(wx_b)
    return weights, biases, outputs


def _loss(pred, ys):
    log_loss = tf.reduce_mean(- ys*tf.log(pred) - (1-ys)*tf.log(1-pred))  # 请自行尝试MSE和交叉熵 对AUC的影响
    return log_loss


def train_step(learning_rate, loss):
    train_step = tf.train.AdamOptimizer(learning_rate).minimize(loss, global_step=global_step)  # 动态lr
    return train_step


train_path = my_input_fn('./nlp/train.tfrecord')    # shape [25, None]


informative_terms = ("bad", "great", "best", "worst", "fun", "beautiful",
                     "excellent", "poor", "boring", "awful", "terrible",
                     "definitely", "perfect", "liked", "worse", "waste",
                     "entertaining", "loved", "unfortunately", "amazing",
                     "enjoyed", "favorite", &#