Python tflearn.lstm函数代码示例

def run():
    # imagine cnn, the third dim is like the 'chnl'
    g = tflearn.input_data(shape=[None, maxlen, len(char_idx)])
    g = tflearn.lstm(g, 512, return_seq=True)
    g = tflearn.dropout(g, 0.5)
    g = tflearn.lstm(g, 512)
    g = tflearn.dropout(g, 0.5)
    g = tflearn.fully_connected(g, len(char_idx), activation='softmax')
    g = tflearn.regression(g, optimizer='adam',
                           loss='categorical_crossentropy',
                           learning_rate=0.001)

    m = tflearn.SequenceGenerator(g, dictionary=char_idx,
                                  seq_maxlen=maxlen,
                                  clip_gradients=5.0,
                                  checkpoint_path='models/model_us_cities')

    for i in range(40):
        seed = random_sequence_from_textfile(path, maxlen)
        m.fit(X, Y, validation_set=0.1, batch_size=128,
              n_epoch=1, run_id='us_cities')
        print("-- TESTING...")
        print("-- Test with temperature of 1.2 --")
        print(m.generate(30, temperature=1.2, seq_seed=seed))
        print("-- Test with temperature of 1.0 --")
        print(m.generate(30, temperature=1.0, seq_seed=seed))
        print("-- Test with temperature of 0.5 --")
        print(m.generate(30, temperature=0.5, seq_seed=seed))

def do_rnn(x_train,x_test,y_train,y_test):
    global n_words
    # Data preprocessing
    # Sequence padding
    print "GET n_words embedding %d" % n_words


    #x_train = pad_sequences(x_train, maxlen=100, value=0.)
    #x_test = pad_sequences(x_test, maxlen=100, value=0.)
    # Converting labels to binary vectors
    y_train = to_categorical(y_train, nb_classes=2)
    y_test = to_categorical(y_test, nb_classes=2)

    # Network building
    net = tflearn.input_data(shape=[None, 100,n_words])
    net = tflearn.lstm(net, 10,  return_seq=True)
    net = tflearn.lstm(net, 10, )
    net = tflearn.fully_connected(net, 2, activation='softmax')
    net = tflearn.regression(net, optimizer='adam', learning_rate=0.1,name="output",
                             loss='categorical_crossentropy')

    # Training

    model = tflearn.DNN(net, tensorboard_verbose=3)
    model.fit(x_train, y_train, validation_set=(x_test, y_test), show_metric=True,
             batch_size=32,run_id="maidou")

def get_model_action():
    # Network building
    net = tflearn.input_data(shape=[None, 10, 128], name='net2_layer1')
    net = tflearn.lstm(net, n_units=256, return_seq=True, name='net2_layer2')
    net = tflearn.dropout(net, 0.6, name='net2_layer3')
    net = tflearn.lstm(net, n_units=256, return_seq=False, name='net2_layer4')
    net = tflearn.dropout(net, 0.6, name='net2_layer5')
    net = tflearn.fully_connected(net, 5, activation='softmax', name='net2_layer6')
    net = tflearn.regression(net, optimizer='sgd', loss='categorical_crossentropy', learning_rate=0.001,
                             name='net2_layer7')
    return tflearn.DNN(net, clip_gradients=5.0, tensorboard_verbose=0)

def sentnet_LSTM_gray(width, height, frame_count, lr, output=9):
    network = input_data(shape=[None, width, height], name='input')
    #network = tflearn.input_data(shape=[None, 28, 28], name='input')
    network = tflearn.lstm(network, 128, return_seq=True)
    network = tflearn.lstm(network, 128)
    network = tflearn.fully_connected(network, 9, activation='softmax')
    network = tflearn.regression(network, optimizer='adam',
    loss='categorical_crossentropy', name="output1")

    model = tflearn.DNN(network, checkpoint_path='model_lstm',
                        max_checkpoints=1, tensorboard_verbose=0, tensorboard_dir='log')

    return model

def do_rnn(X, Y, testX, testY):
    X = np.reshape(X, (-1, 28, 28))
    testX = np.reshape(testX, (-1, 28, 28))

    net = tflearn.input_data(shape=[None, 28, 28])
    net = tflearn.lstm(net, 128, return_seq=True)
    net = tflearn.lstm(net, 128)
    net = tflearn.fully_connected(net, 10, activation='softmax')
    net = tflearn.regression(net, optimizer='adam',
                         loss='categorical_crossentropy', name="output1")
    model = tflearn.DNN(net, tensorboard_verbose=2)
    model.fit(X, Y, n_epoch=1, validation_set=(testX,testY), show_metric=True,
          snapshot_step=100)

def shakespeare():


    path = "shakespeare_input.txt"
    #path = "shakespeare_input-100.txt"
    char_idx_file = 'char_idx.pickle'

    if not os.path.isfile(path):
        urllib.request.urlretrieve(
            "https://raw.githubusercontent.com/tflearn/tflearn.github.io/master/resources/shakespeare_input.txt", path)

    maxlen = 25

    char_idx = None
    if os.path.isfile(char_idx_file):
        print('Loading previous char_idx')
        char_idx = pickle.load(open(char_idx_file, 'rb'))

    X, Y, char_idx = \
        textfile_to_semi_redundant_sequences(path, seq_maxlen=maxlen, redun_step=3,
                                             pre_defined_char_idx=char_idx)

    pickle.dump(char_idx, open(char_idx_file, 'wb'))

    g = tflearn.input_data([None, maxlen, len(char_idx)])
    g = tflearn.lstm(g, 512, return_seq=True)
    g = tflearn.dropout(g, 0.5)
    g = tflearn.lstm(g, 512, return_seq=True)
    g = tflearn.dropout(g, 0.5)
    g = tflearn.lstm(g, 512)
    g = tflearn.dropout(g, 0.5)
    g = tflearn.fully_connected(g, len(char_idx), activation='softmax')
    g = tflearn.regression(g, optimizer='adam', loss='categorical_crossentropy',
                           learning_rate=0.001)

    m = tflearn.SequenceGenerator(g, dictionary=char_idx,
                                  seq_maxlen=maxlen,
                                  clip_gradients=5.0,
                                  checkpoint_path='model_shakespeare')

    for i in range(50):
        seed = random_sequence_from_textfile(path, maxlen)
        m.fit(X, Y, validation_set=0.1, batch_size=128,
              n_epoch=1, run_id='shakespeare')
        print("-- TESTING...")
        print("-- Test with temperature of 1.0 --")
        print(m.generate(600, temperature=1.0, seq_seed=seed))
        #print(m.generate(10, temperature=1.0, seq_seed=seed))
        print("-- Test with temperature of 0.5 --")
        print(m.generate(600, temperature=0.5, seq_seed=seed))

def main():
    load_vectors("./vectors.bin")
    init_seq()
    xlist = []
    ylist = []
    test_X = None
    #for i in range(len(seq)-100):
    for i in range(1000):
        sequence = seq[i:i+20]
        xlist.append(sequence)
        ylist.append(seq[i+20])
        if test_X is None:
            test_X = np.array(sequence)
            (match_word, max_cos) = vector2word(seq[i+20])
            print "right answer=", match_word, max_cos

    X = np.array(xlist)
    Y = np.array(ylist)
    net = tflearn.input_data([None, 20, 200])
    net = tflearn.lstm(net, 200)
    net = tflearn.fully_connected(net, 200, activation='linear')
    net = tflearn.regression(net, optimizer='sgd', learning_rate=0.1,
                                     loss='mean_square')
    model = tflearn.DNN(net)
    model.fit(X, Y, n_epoch=1000, batch_size=1,snapshot_epoch=False,show_metric=True)
    model.save("model")
    predict = model.predict([test_X])
    #print predict
    #for v in test_X:
    #    print vector2word(v)
    (match_word, max_cos) = vector2word(predict[0])
    print "predict=", match_word, max_cos

def do_rnn(x,y):
    global max_document_length
    print "RNN"
    trainX, testX, trainY, testY = train_test_split(x, y, test_size=0.4, random_state=0)
    y_test=testY

    trainX = pad_sequences(trainX, maxlen=max_document_length, value=0.)
    testX = pad_sequences(testX, maxlen=max_document_length, value=0.)
    # Converting labels to binary vectors
    trainY = to_categorical(trainY, nb_classes=2)
    testY = to_categorical(testY, nb_classes=2)

    # Network building
    net = tflearn.input_data([None, max_document_length])
    net = tflearn.embedding(net, input_dim=10240000, output_dim=128)
    net = tflearn.lstm(net, 128, dropout=0.8)
    net = tflearn.fully_connected(net, 2, activation='softmax')
    net = tflearn.regression(net, optimizer='adam', learning_rate=0.001,
                             loss='categorical_crossentropy')

    # Training
    model = tflearn.DNN(net, tensorboard_verbose=0)
    model.fit(trainX, trainY, validation_set=0.1, show_metric=True,
              batch_size=10,run_id="webshell",n_epoch=5)

    y_predict_list=model.predict(testX)
    y_predict=[]
    for i in y_predict_list:
        if i[0] > 0.5:
            y_predict.append(0)
        else:
            y_predict.append(1)

    do_metrics(y_test, y_predict)

def do_rnn(trainX, testX, trainY, testY):
    global n_words
    # Data preprocessing
    # Sequence padding
    print "GET n_words embedding %d" % n_words


    trainX = pad_sequences(trainX, maxlen=MAX_DOCUMENT_LENGTH, value=0.)
    testX = pad_sequences(testX, maxlen=MAX_DOCUMENT_LENGTH, value=0.)
    # Converting labels to binary vectors
    trainY = to_categorical(trainY, nb_classes=2)
    testY = to_categorical(testY, nb_classes=2)

    # Network building
    net = tflearn.input_data([None, MAX_DOCUMENT_LENGTH])
    net = tflearn.embedding(net, input_dim=n_words, output_dim=128)
    net = tflearn.lstm(net, 128, dropout=0.8)
    net = tflearn.fully_connected(net, 2, activation='softmax')
    net = tflearn.regression(net, optimizer='adam', learning_rate=0.001,
                             loss='categorical_crossentropy')

    # Training



    model = tflearn.DNN(net, tensorboard_verbose=3)
    model.fit(trainX, trainY, validation_set=(testX, testY), show_metric=True,
             batch_size=32,run_id="maidou")

def do_rnn(trainX, testX, trainY, testY):
    max_document_length=64
    y_test=testY
    trainX = pad_sequences(trainX, maxlen=max_document_length, value=0.)
    testX = pad_sequences(testX, maxlen=max_document_length, value=0.)
    # Converting labels to binary vectors
    trainY = to_categorical(trainY, nb_classes=2)
    testY = to_categorical(testY, nb_classes=2)

    # Network building
    net = tflearn.input_data([None, max_document_length])
    net = tflearn.embedding(net, input_dim=10240000, output_dim=64)
    net = tflearn.lstm(net, 64, dropout=0.1)
    net = tflearn.fully_connected(net, 2, activation='softmax')
    net = tflearn.regression(net, optimizer='adam', learning_rate=0.001,
                             loss='categorical_crossentropy')

    # Training
    model = tflearn.DNN(net, tensorboard_verbose=0,tensorboard_dir="dga_log")
    model.fit(trainX, trainY, validation_set=(testX, testY), show_metric=True,
              batch_size=10,run_id="dga",n_epoch=1)

    y_predict_list = model.predict(testX)
    #print y_predict_list

    y_predict = []
    for i in y_predict_list:
        print  i[0]
        if i[0] > 0.5:
            y_predict.append(0)
        else:
            y_predict.append(1)

    print(classification_report(y_test, y_predict))
    print metrics.confusion_matrix(y_test, y_predict)

    def test_sequencegenerator(self):

        with tf.Graph().as_default():
            text = "123456789101234567891012345678910123456789101234567891012345678910"
            maxlen = 5

            X, Y, char_idx = \
                tflearn.data_utils.string_to_semi_redundant_sequences(text, seq_maxlen=maxlen, redun_step=3)

            g = tflearn.input_data(shape=[None, maxlen, len(char_idx)])
            g = tflearn.lstm(g, 32)
            g = tflearn.dropout(g, 0.5)
            g = tflearn.fully_connected(g, len(char_idx), activation='softmax')
            g = tflearn.regression(g, optimizer='adam', loss='categorical_crossentropy',
                                   learning_rate=0.1)

            m = tflearn.SequenceGenerator(g, dictionary=char_idx,
                                          seq_maxlen=maxlen,
                                          clip_gradients=5.0)
            m.fit(X, Y, validation_set=0.1, n_epoch=100, snapshot_epoch=False)
            res = m.generate(10, temperature=1., seq_seed="12345")
            self.assertEqual(res, "123456789101234", "SequenceGenerator test failed! Generated sequence: " + res + " expected '123456789101234'")

            # Testing save method
            m.save("test_seqgen.tflearn")
            self.assertTrue(os.path.exists("test_seqgen.tflearn"))

            # Testing load method
            m.load("test_seqgen.tflearn")
            res = m.generate(10, temperature=1., seq_seed="12345")
            self.assertEqual(res, "123456789101234", "SequenceGenerator test failed after loading model! Generated sequence: " + res + " expected '123456789101234'")

def generator_xss():
    global char_idx
    global xss_data_file
    global maxlen


    if os.path.isfile(char_idx_file):
        print('Loading previous xxs_char_idx')
        char_idx = pickle.load(open(char_idx_file, 'rb'))


    X, Y, char_idx = \
        textfile_to_semi_redundant_sequences(xss_data_file, seq_maxlen=maxlen, redun_step=3,
                                             pre_defined_char_idx=char_idx)


    #pickle.dump(char_idx, open(char_idx_file, 'wb'))

    g = tflearn.input_data([None, maxlen, len(char_idx)])
    g = tflearn.lstm(g, 32, return_seq=True)
    g = tflearn.dropout(g, 0.1)
    g = tflearn.lstm(g, 32, return_seq=True)
    g = tflearn.dropout(g, 0.1)
    g = tflearn.lstm(g, 32)
    g = tflearn.dropout(g, 0.1)
    g = tflearn.fully_connected(g, len(char_idx), activation='softmax')
    g = tflearn.regression(g, optimizer='adam', loss='categorical_crossentropy',
                           learning_rate=0.001)

    m = tflearn.SequenceGenerator(g, dictionary=char_idx,
                                  seq_maxlen=maxlen,
                                  clip_gradients=5.0,
                                  checkpoint_path='chkpoint/model_scanner_poc')

    print "random_sequence_from_textfile"
    #seed = random_sequence_from_textfile(xss_data_file, maxlen)
    seed='"/><script>'
    m.fit(X, Y, validation_set=0.1, batch_size=128,
              n_epoch=2, run_id='scanner-poc')
    print("-- TESTING...")

    print("-- Test with temperature of 0.1 --")
    print(m.generate(32, temperature=0.1, seq_seed=seed))
    print("-- Test with temperature of 0.5 --")
    print(m.generate(32, temperature=0.5, seq_seed=seed))
    print("-- Test with temperature of 1.0 --")
    print(m.generate(32, temperature=1.0, seq_seed=seed))

def build(embedding_size=(400000, 50), train_embedding=False, hidden_dims=128,
          learning_rate=0.001):
    net = tflearn.input_data([None, 200])
    net = tflearn.embedding(net, input_dim=embedding_size[0],
                            output_dim=embedding_size[1],
                            trainable=train_embedding, name='EmbeddingLayer')
    net = tflearn.lstm(net, hidden_dims, return_seq=True)
    net = tflearn.dropout(net, 0.5)
    net = tflearn.lstm(net, hidden_dims, return_seq=True)
    net = tflearn.dropout(net, 0.5)
    net = tflearn.lstm(net, hidden_dims, return_seq=True)
    net = tflearn.dropout(net, 0.5)
    net = tflearn.lstm(net, hidden_dims)
    net = tflearn.dropout(net, 0.5)
    net = tflearn.fully_connected(net, 2, activation='softmax')
    net = tflearn.regression(net, optimizer='adam', learning_rate=learning_rate,
                             loss='categorical_crossentropy')
    return net

def generate_net(embedding):
    net = tflearn.input_data([None, 200])
    net = tflearn.embedding(net, input_dim=300000, output_dim=128)
    net = tflearn.lstm(net, 128)
    net = tflearn.dropout(net, 0.5)
    net = tflearn.fully_connected(net, 2, activation='softmax')
    net = tflearn.regression(net, optimizer='adam',
                             loss='categorical_crossentropy')
    return net

def create_net(in_sx, in_sy, out_sx):
	"""
	Creates a tflearn neural network with the correct
	architecture for learning to hear the keyword
	"""
	net = tflearn.input_data([None, in_sx, in_sy])
	net = tflearn.lstm(net, lstm_size, dropout=lstm_dropout)
	net = tflearn.fully_connected(net, out_sx, activation='softmax')
	net = tflearn.regression(net, learning_rate=learning_rate, optimizer='adam', loss='categorical_crossentropy')
	return net