Skip to main content
 首页 » 编程设计

python之张量形状错误 : Must be rank 2 but is rank 3

2025年02月15日9birdshome

我很难搜索可以帮助我构建文本序列(特征)分类器的文档、研究或博客。我拥有的文本序列包含网络日志。

我正在使用 TensorFlow 构建 GRU 模型,并将 SVM 作为分类函数。我在处理张量形状时遇到了问题。它说 ValueError: Shape must be rank 2 but is rank 3 for 'MatMul' (op: 'MatMul') with input shapes: [?,23,1], [512,2]。 Here is a sample我用来训练我的神经网络的数据。

我的项目的目标是使用这个 GRU-SVM 模型在 Kyoto University's honeypot system intrusion detection dataset 上进行入侵检测。 .该数据集有 23 个特征和一个标签(如果网络中存在入侵或没有)。

import data 
import numpy as np 
import os 
import tensorflow as tf 
 
 
BATCH_SIZE = 200 
CELLSIZE = 512 
NLAYERS = 3 
SVMC = 1 
learning_rate = 0.01 
 
TRAIN_PATH = '/home/darth/GitHub Projects/gru_svm/dataset/train/6' 
 
def main(): 
    examples, labels, keys = data.input_pipeline(path=TRAIN_PATH, batch_size=BATCH_SIZE, num_epochs=1) 
 
    seqlen = examples.shape[1] 
 
    x = tf.placeholder(shape=[None, seqlen, 1], dtype=tf.float32) 
    y = tf.placeholder(shape=[None, 2], dtype=tf.float32) 
    Hin = tf.placeholder(shape=[None, CELLSIZE*NLAYERS], dtype=tf.float32) 
 
    # cell = tf.contrib.rnn.GRUCell(CELLSIZE) 
    network = [] 
    for index in range(NLAYERS): 
        network.append(tf.contrib.rnn.GRUCell(CELLSIZE)) 
 
    mcell = tf.contrib.rnn.MultiRNNCell(network, state_is_tuple=False) 
    Hr, H = tf.nn.dynamic_rnn(mcell, x, initial_state=Hin, dtype=tf.float32) 
 
    Hf = tf.transpose(Hr, [1, 0, 2]) 
    last = tf.gather(Hf, int(Hf.get_shape()[0]) - 1) 
 
    weight = tf.Variable(tf.truncated_normal([CELLSIZE, 2], stddev=0.01), tf.float32) 
    bias = tf.Variable(tf.constant(0.1, shape=[2])) 
    logits = tf.matmul(last, weight) + bias 
 
    regularization_loss = 0.5 * tf.reduce_sum(tf.square(weight)) 
    hinge_loss = tf.reduce_sum(tf.maximum(tf.zeros([BATCH_SIZE, 1]), 1 - y * logits)) 
    loss = regularization_loss + SVMC * hinge_loss 
 
    train_step = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(loss) 
 
    init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer()) 
 
    with tf.Session() as sess: 
        sess.run(init_op) 
 
        train_loss = 0 
 
        coord = tf.train.Coordinator() 
        threads = tf.train.start_queue_runners(coord=coord) 
 
        try: 
            for index in range(100): 
                for j in range(1000): 
                    example_batch, label_batch, key_batch = sess.run([examples, labels, keys]) 
                    _, train_loss_ = sess.run([train_step, loss], 
                        feed_dict = { x : example_batch, 
                                        y : label_batch, 
                                        Hin : np.zeros([BATCH_SIZE, CELLSIZE * NLAYERS]) 
                                    }) 
                    train_loss += train_loss_ 
                print('[{}] loss : {}'.format(index, (train_loss / 1000))) 
                train_loss = 0 
        except tf.errors.OutOfRangeError: 
            print('EOF reached.') 
        except KeyboardInterrupt: 
            print('Interrupted by user at {}'.format(index)) 
        finally: 
            coord.request_stop() 
        coord.join(threads) 
 
main() 

注意:我之所以构建我的 MultiRNNCell 是因为我遇到了一个类似于 post 的错误.

network = [] 
for index in range(NLAYERS): 
    network.append(tf.contrib.rnn.GRUCell(CELLSIZE)) 

预先感谢您的回复!

2017 年 8 月 1 日更新 源代码根据@jdehesa 的建议进行了改进:

import data 
import numpy as np 
import os 
import tensorflow as tf 
 
 
BATCH_SIZE = 200 
CELLSIZE = 512 
NLAYERS = 3 
SVMC = 1 
learning_rate = 0.01 
 
TRAIN_PATH = '/home/darth/GitHub Projects/gru_svm/dataset/train/6' 
 
def main(): 
    examples, labels, keys = data.input_pipeline(path=TRAIN_PATH, batch_size=BATCH_SIZE, num_epochs=1) 
 
    seqlen = examples.shape[1] 
 
    x = tf.placeholder(shape=[None, seqlen, 1], dtype=tf.float32, name='x') 
    y_input = tf.placeholder(shape=[None], dtype=tf.int32, name='y_input') 
    y = tf.one_hot(y_input, 2, dtype=tf.float32, name='y') 
    Hin = tf.placeholder(shape=[None, CELLSIZE*NLAYERS], dtype=tf.float32, name='Hin') 
 
    network = [] 
    for index in range(NLAYERS): 
        network.append(tf.contrib.rnn.GRUCell(CELLSIZE)) 
 
    mcell = tf.contrib.rnn.MultiRNNCell(network, state_is_tuple=False) 
    Hr, H = tf.nn.dynamic_rnn(mcell, x, initial_state=Hin, dtype=tf.float32) 
 
    Hf = tf.transpose(Hr, [1, 0, 2]) 
    last = tf.gather(Hf, int(Hf.get_shape()[0]) - 1) 
 
    weight = tf.Variable(tf.truncated_normal([CELLSIZE, 2], stddev=0.01), tf.float32, name='weights') 
    bias = tf.Variable(tf.constant(0.1, shape=[2]), name='bias') 
    logits = tf.matmul(last, weight) + bias 
 
    regularization_loss = 0.5 * tf.reduce_sum(tf.square(weight)) 
    hinge_loss = tf.reduce_sum(tf.maximum(tf.zeros([BATCH_SIZE, 1]), 1 - y * logits)) 
    loss = regularization_loss + SVMC * hinge_loss 
 
    train_step = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(loss) 
 
    init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer()) 
 
    with tf.Session() as sess: 
        sess.run(init_op) 
 
        train_loss = 0 
 
        coord = tf.train.Coordinator() 
        threads = tf.train.start_queue_runners(coord=coord) 
 
        try: 
            for index in range(100): 
                example_batch, label_batch, key_batch = sess.run([examples, labels, keys]) 
                _, train_loss_ = sess.run([train_step, loss], 
                    feed_dict = { x : example_batch[..., np.newaxis], 
                                    y_input : label_batch, 
                                    Hin : np.zeros([BATCH_SIZE, CELLSIZE * NLAYERS]) 
                                }) 
                train_loss += train_loss_ 
                print('[{}] loss : {}'.format(index, (train_loss / 1000))) 
                print('Weights : {}'.format(sess.run(weight))) 
                print('Biases : {}'.format(sess.run(bias))) 
                train_loss = 0 
        except tf.errors.OutOfRangeError: 
            print('EOF reached.') 
        except KeyboardInterrupt: 
            print('Interrupted by user at {}'.format(index)) 
        finally: 
            coord.request_stop() 
        coord.join(threads) 
 
main() 

我的下一步是验证我得到的结果是否正确。

请您参考如下方法:

问题出在行中:

logits = tf.matmul(x, weight) + bias 

我想你的意思是:

logits = tf.matmul(last, weight) + bias