使用Tensorflow和我们自己的数据进行训练时出错

Question

I am using Tensorflow for training for developing the model to detect whether the message is spam or not. I am using Python .

My training data size is 3000 rows and 3 columns, and the size of test data is 2700 rows and 3 columns.

Batch size: 500

n_nodes_hl1 = 500
n_nodes_hl2 = 500

n_classes = 2

batch_size = 32
total_batches = int(3000 / batch_size)
hm_epochs = 10

x = tf.placeholder('float')
y = tf.placeholder('float')

hidden_1_layer = {'f_fum': n_nodes_hl1,
                  'weight': tf.Variable(tf.random_normal([3000, n_nodes_hl1])),
                  'bias': tf.Variable(tf.random_normal([n_nodes_hl1]))}

hidden_2_layer = {'f_fum': n_nodes_hl2,
                  'weight': tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
                  'bias': tf.Variable(tf.random_normal([n_nodes_hl2]))}

output_layer = {'f_fum': None,
                'weight': tf.Variable(tf.random_normal([n_nodes_hl2, n_classes])),
                'bias': tf.Variable(tf.random_normal([n_classes])), }

I am getting this error during compilation:

WARNING:tensorflow:From saving_and_restoring.py:50: softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version.
Instructions for updating:

Future major versions of TensorFlow will allow gradients to flow
into the labels input on backprop by default.

See @{tf.nn.softmax_cross_entropy_with_logits_v2}.

Traceback (most recent call last):
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1322, in _do_call
    return fn(*args)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1307, in _run_fn
    options, feed_dict, fetch_list, target_list, run_metadata)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1409, in _call_tf_sessionrun
    run_metadata)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Matrix size-incompatible: In[0]: [32,12], In[1]: [2794,500]
     [[Node: MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_Placeholder_0_0, Variable/read)]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "saving_and_restoring.py", line 103, in <module>
    train_neural_network(x)
  File "saving_and_restoring.py", line 89, in train_neural_network
    y: np.array(batch_y)})
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 900, in run
    run_metadata_ptr)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1135, in _run
    feed_dict_tensor, options, run_metadata)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1316, in _do_run
    run_metadata)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1335, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Matrix size-incompatible: In[0]: [32,12], In[1]: [2794,500]
     [[Node: MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_Placeholder_0_0, Variable/read)]]

Caused by op 'MatMul', defined at:
  File "saving_and_restoring.py", line 103, in <module>
    train_neural_network(x)
  File "saving_and_restoring.py", line 49, in train_neural_network
    prediction = neural_network_model(x)
  File "saving_and_restoring.py", line 36, in neural_network_model
    l1 = tf.add(tf.matmul(data, hidden_1_layer['weight']), hidden_1_layer['bias'])
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/math_ops.py", line 2122, in matmul
    a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gen_math_ops.py", line 4279, in mat_mul
    name=name)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 3392, in create_op
    op_def=op_def)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 1718, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): Matrix size-incompatible: In[0]: [32,12], In[1]: [2794,500]
     [[Node: MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_Placeholder_0_0, Variable/read)]]

Python version is 3.6 and I am using nltk for sentimental analysis.

Please help.

Thanks.

EDIT

train_set_shuffled.csv shape=(2792,3)

My code:

import tensorflow as tf
import pickle
import numpy as np
import nltk
from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer

lemmatizer = WordNetLemmatizer()

n_nodes_hl1 = 500
n_nodes_hl2 = 500

n_classes = 2
columns=3
batch_size = 32
total_batches = int(3000 / batch_size)
hm_epochs = 10

x = tf.placeholder( tf.float32)
y = tf.placeholder( tf.float32)

hidden_1_layer = {'f_fum': n_nodes_hl1,
                  'weight': tf.Variable(tf.random_normal([3000, n_nodes_hl1])),
                  'bias': tf.Variable(tf.random_normal([n_nodes_hl1]))}

hidden_2_layer = {'f_fum': n_nodes_hl2,
                  'weight': tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
                  'bias': tf.Variable(tf.random_normal([n_nodes_hl2]))}

output_layer = {'f_fum': None,
                'weight': tf.Variable(tf.random_normal([n_nodes_hl2, n_classes])),
                'bias': tf.Variable(tf.random_normal([n_classes])), }


def neural_network_model(data):
    l1 = tf.add(tf.matmul(data, hidden_1_layer['weight']), hidden_1_layer['bias'])
    l1 = tf.nn.relu(l1)
    l2 = tf.add(tf.matmul(l1, hidden_2_layer['weight']), hidden_2_layer['bias'])
    l2 = tf.nn.relu(l2)
    output = tf.matmul(l2, output_layer['weight']) + output_layer['bias']
    return output


saver = tf.train.Saver()
tf_log = 'tf.log'


def train_neural_network(x):
    prediction = neural_network_model(x)
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y))
    optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        try:
            epoch = int(open(tf_log, 'r').read().split('\n')[-2]) + 1
            print('STARTING:', epoch)
        except:
            epoch = 1

        while epoch <= hm_epochs:
            if epoch != 1:
                saver.restore(sess, "model.ckpt")
            epoch_loss = 1
            with open('lexicon-2500-2638.pickle', 'rb') as f:
                lexicon = pickle.load(f)
            with open('train_set_shuffled.csv', buffering=20000, encoding='latin-1') as f:
                batch_x = []
                batch_y = []
                batches_run = 0
                for line in f:
                    label = line.split(':::')[0]
                    tweet = line.split(':::')[1]
                    current_words = word_tokenize(tweet.lower())
                    current_words = [lemmatizer.lemmatize(i) for i in current_words]

                    features = np.zeros(len(lexicon))

                    for word in current_words:
                        if word.lower() in lexicon:
                            index_value = lexicon.index(word.lower())
                            # OR DO +=1, test both
                            features[index_value] += 1
                    line_x = list(features)
                    line_y = eval(label)
                    batch_x.append(line_x)
                    batch_y.append(line_y)
                    if len(batch_x) >= batch_size:
                        _, c = sess.run([optimizer, cost], feed_dict={x: np.array(batch_x),
                                                                      y: np.array(batch_y)})
                        epoch_loss += c
                        batch_x = []
                        batch_y = []
                        batches_run += 1
                        print('Batch run:', batches_run, '/', total_batches, '| Epoch:', epoch, '| Batch Loss:', c, )

            saver.save(sess, "model.ckpt")
            print('Epoch', epoch, 'completed out of', hm_epochs, 'loss:', epoch_loss)
            with open(tf_log, 'a') as f:
                f.write(str(epoch) + '\n')
            epoch += 1


train_neural_network(x)


def test_neural_network():
    prediction = neural_network_model(x)
    with tf.Session() as sess:
        sess.run(tf.initialize_all_variables())
        for epoch in range(hm_epochs):
            try:
                saver.restore(sess, "model.ckpt")
            except Exception as e:
                print(str(e))
            epoch_loss = 0

        correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
        accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
        feature_sets = []
        labels = []
        counter = 0
        with open('processed-test-set.csv', buffering=20000) as f:
            for line in f:
                try:
                    features = list(eval(line.split('::')[0]))
                    label = list(eval(line.split('::')[1]))
                    feature_sets.append(features)
                    labels.append(label)
                    counter += 1
                except:
                    pass
        print('Tested', counter, 'samples.')
        test_x = np.array(feature_sets)
        test_y = np.array(labels)
        print('Accuracy:', accuracy.eval({x: test_x, y: test_y}))


test_neural_network()

EDIT 2

feature_colum_size=12
x = tf.placeholder(tf.float32,shape=[batch_size,feature_colum_size])
y = tf.placeholder(tf.float32,shape=[batch_size,feature_colum_size])

hidden_1_layer = {'f_fum': n_nodes_hl1,
                  'weight': tf.Variable(tf.random_normal([feature_colum_size, n_nodes_hl1])),
                  'bias': tf.Variable(tf.random_normal([n_nodes_hl1]))}

hidden_2_layer = {'f_fum': n_nodes_hl2,
                  'weight': tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
                  'bias': tf.Variable(tf.random_normal([n_nodes_hl2]))}

output_layer = {'f_fum': None,
                'weight': tf.Variable(tf.random_normal([n_nodes_hl2, n_classes])),
                'bias': tf.Variable(tf.random_normal([n_classes])), }

Answer 1

I think the problem is where you are generating your input data(batch_x). It seems that your input shape is [batch_size,12] that you are multiplying(matmul) your hidden layer( hidden_layer1["weight"] ) of shape of [ 3000,n_nodes_hl1 ] causing the matrix mutliplication operation to fail. and the way reading and parsing lines from train_shuffled is done makes me think that the input feature size(12) is not consistent.

What i think you should do .

Fix the input_feature size x = tf.placeholder('float') to x = tf.placeholder(tf.float32,shape=[batch_size,feature_colum_size])

change the 'weight': tf.Variable(tf.random_normal([3000, n_nodes_hl1])) to

'weight': tf.Variable(tf.random_normal([feature_column_size, n_nodes_hl1])),

feature_column_size should be consistent between your input and the first hidden layer inorder to be able to perform matmul multiplication.