使用CNN做文本分类

    from __future__ import division, print_function, absolute_import
    import tensorflow as tf
    import tflearn
    from tflearn.layers.core import input_data, dropout, fully_connected
    from tflearn.layers.conv import conv_1d, global_max_pool
    from tflearn.layers.merge_ops import merge
    from tflearn.layers.estimator import regression
    from tflearn.data_utils import to_categorical, pad_sequences
    from tflearn.datasets import imdb
    import pickle
    import numpy as np
    """
    还是加载imdb.pkl数据
    """
    train, test, _ = imdb.load_data(path='imdb.pkl', n_words=10000,
                                    valid_portion=0.1)
    trainX, trainY = train
    testX, testY = test
    """
    转化为固定长度的向量,这里固定长度为100
    """
    trainX = pad_sequences(trainX, maxlen=100, value=0.)
    testX = pad_sequences(testX, maxlen=100, value=0.)
    """
    二值化向量
    """
    trainY = to_categorical(trainY, nb_classes=2)
    testY = to_categorical(testY, nb_classes=2)
    """
    构建卷积神经网络,这里卷积神经网网络为1d卷积
    """
    network = input_data(shape=[None, 100], name='input')
    network = tflearn.embedding(network, input_dim=10000, output_dim=128)
    branch1 = conv_1d(network, 128, 3, padding='valid', activation='relu', regularizer="L2")
    branch2 = conv_1d(network, 128, 4, padding='valid', activation='relu', regularizer="L2")
    branch3 = conv_1d(network, 128, 5, padding='valid', activation='relu', regularizer="L2")
    network = merge([branch1, branch2, branch3], mode='concat', axis=1)
    network = tf.expand_dims(network, 2)
    network = global_max_pool(network)
    network = dropout(network, 0.5)
    network = fully_connected(network, 2, activation='softmax')
    network = regression(network, optimizer='adam', learning_rate=0.001,
                         loss='categorical_crossentropy', name='target')
    """
    训练开始
    """
    model = tflearn.DNN(network, tensorboard_verbose=0)
    model.fit(trainX, trainY, n_epoch = 1, shuffle=True, validation_set=(testX, testY), show_metric=True, batch_size=32)
    """
    模型保存
    """
    model.save("cnn.model")
    """
    做测试使用
    """
    test=np.linspace(1,101,100).reshape(1,100)
    print("测试结果:",model.predict(test))

模型训练结果以及模型保存情况:

    Training Step: 697  | total loss: 0.40838 | time: 79.960s
    | Adam | epoch: 001 | loss: 0.40838 - acc: 0.8247 -- iter: 22304/22500
    Training Step: 698  | total loss: 0.39128 | time: 80.112s
    | Adam | epoch: 001 | loss: 0.39128 - acc: 0.8329 -- iter: 22336/22500
    Training Step: 699  | total loss: 0.38896 | time: 80.298s
    | Adam | epoch: 001 | loss: 0.38896 - acc: 0.8402 -- iter: 22368/22500
    Training Step: 700  | total loss: 0.39468 | time: 80.456s
    | Adam | epoch: 001 | loss: 0.39468 - acc: 0.8343 -- iter: 22400/22500
    Training Step: 701  | total loss: 0.39380 | time: 80.640s
    | Adam | epoch: 001 | loss: 0.39380 - acc: 0.8353 -- iter: 22432/22500
    Training Step: 702  | total loss: 0.38980 | time: 80.787s
    | Adam | epoch: 001 | loss: 0.38980 - acc: 0.8392 -- iter: 22464/22500
    Training Step: 703  | total loss: 0.39020 | time: 80.970s
    | Adam | epoch: 001 | loss: 0.39020 - acc: 0.8397 -- iter: 22496/22500
    Training Step: 704  | total loss: 0.38543 | time: 82.891s
    | Adam | epoch: 001 | loss: 0.38543 - acc: 0.8370 | val_loss: 0.44625 - val_acc: 0.7880 -- iter: 22500/22500
    --
    测试结果: [[ 0.77064246  0.2293576 ]]




加载模型并做预测:

    import tensorflow as tf
    import numpy as np
    import tflearn
    from tflearn.layers.core import input_data, dropout, fully_connected
    from tflearn.layers.conv import conv_1d, global_max_pool
    from tflearn.layers.merge_ops import merge
    from tflearn.layers.estimator import regression
    """
    跟训练模型的网络结构一样
    """
    network = input_data(shape=[None, 100], name='input')
    network = tflearn.embedding(network, input_dim=10000, output_dim=128)
    branch1 = conv_1d(network, 128, 3, padding='valid', activation='relu', regularizer="L2")
    branch2 = conv_1d(network, 128, 4, padding='valid', activation='relu', regularizer="L2")
    branch3 = conv_1d(network, 128, 5, padding='valid', activation='relu', regularizer="L2")
    network = merge([branch1, branch2, branch3], mode='concat', axis=1)
    network = tf.expand_dims(network, 2)
    network = global_max_pool(network)
    network = dropout(network, 0.5)
    network = fully_connected(network, 2, activation='softmax')
    network = regression(network, optimizer='adam', learning_rate=0.001,
                         loss='categorical_crossentropy', name='target')
    """
    加载模型做预测
    """
    model = tflearn.DNN(network)
    model.load("cnn.model")
    test=np.linspace(1,101,100).reshape(1,100)
    # Predict  [[ 0.7725634   0.22743654]]
    prediction = model.predict(test)
    print("模型预测结果",prediction)



结果:

    2017-10-15 19:35:14.940689: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
    模型预测结果 [[ 0.77064246  0.2293576 ]]
    Process finished with exit code 0



基于tflearn高阶api怎么做文本分类基本上完成