英文文本分类（CNN）

最新推荐文章于 2023-05-22 00:35:25 发布

我的天空足够你跳舞

最新推荐文章于 2023-05-22 00:35:25 发布

阅读量8.9k

点赞数 2

分类专栏：深度学习机器学习文章标签： DL 英文文本分类

本文链接：https://blog.csdn.net/weixin_42108215/article/details/82666143

版权

本文介绍了使用卷积神经网络（CNN）进行英文文本分类的实践过程，包括数据预处理、模型训练及效果展示。

摘要由CSDN通过智能技术生成

网络结构参照如下图：

数据预处理阶段：

import numpy as np
import re
import itertools
from collections import Counter


def clean_str(string):
    """
    Tokenization/string cleaning for all datasets except for SST.
    Original taken from https://github.com/yoonkim/CNN_sentence/blob/master/process_data.py
    """
    string = re.sub(r"[^A-Za-z0-9(),!?\'\`]", " ", string)
    string = re.sub(r"\'s", " \'s", string)
    string = re.sub(r"\'ve", " \'ve", string)
    string = re.sub(r"n\'t", " n\'t", string)
    string = re.sub(r"\'re", " \'re", string)
    string = re.sub(r"\'d", " \'d", string)
    string = re.sub(r"\'ll", " \'ll", string)
    string = re.sub(r",", " , ", string)
    string = re.sub(r"!", " ! ", string)
    string = re.sub(r"\(", " \( ", string)
    string = re.sub(r"\)", " \) ", string)
    string = re.sub(r"\?", " \? ", string)
    string = re.sub(r"\s{2,}", " ", string)
    return string.strip().lower()


def load_data_and_labels(positive_data_file, negative_data_file):
    """
    Loads MR polarity data from files, splits the data into words and generates labels.
    Returns split sentences and labels.
    """
    # Load data from files
    
    
    positive = open(positive_data_file, "rb").read().decode('utf-8')
    negative = open(negative_data_file, "rb").read().decode('utf-8')
    
    positive_examples = positive.split('\n')[:-1]
    negative_examples = negative.split('\n')[:-1]
    
    positive_examples = [s.strip() for s in positive_examples]
    negative_examples = [s.strip() for s in negative_examples]
    
    #positive_examples = list(open(positive_data_file, "rb").read().decode('utf-8'))
    #positive_examples = [s.strip() for s in positive_examples]
    #negative_examples = list(open(negative_data_file, "rb").read().decode('utf-8'))
    #negative_examples = [s.strip() for s in negative_examples]
    # Split by words
    x_text = positive_examples + negative_examples
    x_text = [clean_str(sent) for sent in x_text]
    # Generate labels
    positive_labels = [[0, 1] for _ in positive_examples]
    negative_labels = [[1, 0] for _ in negative_examples]
    y = np.concatenate([positive_labels, negative_labels], 0)
    return [x_text, y]


def batch_iter(data, batch_size, num_epochs, shuffle=True):
    """
    Generates a batch iterator for a dataset.
    """
    data = np.array(data)
    data_size = len(data)
    num_batches_per_epoch = int((len(data)-1)/batch_size) + 1
    for epoch in range(num_epochs):
        # Shuffle the data at each epoch
        if shuffle:
            shuffle_indices = np.random.permutation(np.arange(data_size))
            shuffled_data = data[shuffle_indices]
        else:
            shuffled_data = data
        for batch_num in range(num_batches_per_epoch):
            start_index = batch_num * batch_size
            end_index = min((batch_num + 1) * batch_size, data_size)
            yield shuffled_data[start_index:end_index]

#! /usr/bin/env python

import tensorflow as tf
import numpy as np
import os
import time
import datetime
import data_helpers
from text_cnn import TextCNN
from tensorflow.contrib import learn
import csv

# Parameters
# ==================================================

# Data Parameters
tf.flags.DEFINE_string("positive_data_file", "./data/rt-polaritydata/rt-polarity.pos", "Data source for the positive data.")
tf.flags.DEFINE_string("negative_data_file", "./data/rt-polaritydata/rt-polarity.neg", "Data source for the positive data.")

# Eval Parameters
tf.flags.DEFINE_integer("batch_size", 64, "Batch Size (default: 64)")
tf.flags.DEFINE_string("checkpoint_dir", "./", "Checkpoint directory from training run")
tf.flags.DEFINE_boolean("eval_train", False, "Evaluate on all training data")
tf.app.flags.DEFINE_string('f', '', 'kernel')

# Misc Parameters
tf.flags.DEFINE_boolean("allow_soft_placement", True, "Allow device soft device placement")
tf.flags.DEFINE_boolean("log_device_placement", False, "Log placement of ops on devices")


FLAGS = tf.flags.FLAGS
FLAGS.flag_values_dict()
print("\nParameters:")
for attr, value in sorted(FLAGS.__flags.items()):
    print("{}={}".format(attr.upper(), value))
print("")

# CHANGE THIS: Load data. Load your own data here
if FLAGS.eval_train:
    x_raw, y_test = data_helpers.load_data_and_labels(FLAGS.positive_data_file, FLAGS.negative_data_file)
    y_test = np.argmax(y_test, axis=1)
else:
    x_raw = ["a masterpiece four years in the making", "everything is off."]
    y_test = [1, 0]

# Map data into vocabulary
vocab_path = os.path.join(FLAGS.checkpoint_dir, "..", "vocab")
vocab_processor = learn.preprocessing.VocabularyProcessor.restore(vocab_path)
x_test = np.array(list(vocab_processor.transform(x_raw)))

print("\nEvaluating...\n")

# Evaluation
# ==================================================
checkpoint_file = tf.train.latest_checkpoint(FLAGS.checkpoint_dir)
graph = tf.Graph()
with graph.as_default():
    session_conf = tf.ConfigProto(
      allow_soft_placement=FLAGS.allow_soft_placement,
      log_device_placement=FLAGS.log_device_placement)
    sess = tf.Session(config=session_conf)
    with sess.as_default():
        # Load the saved meta graph and restore variables
        saver = tf.train.import_meta_graph("{}.meta".format(checkpoint_file))
        saver.restore(sess, checkpoint_file)

        # Get the placeholders from the graph by name
        input_x = graph.get_operation_by_name("input_x").outputs[0]
        # input_y = graph.get_operation_by_name("input_y").outputs[0]
        dropout_keep_prob = graph.get_operation_by_name("dropout_keep_prob").outputs[0]

        # Tensors we want to evaluate
        predictions = graph.get_operation_by_name("output/predictions").outputs[0]

        # Generate batches for one epoch
        batches = data_helpers.batch_iter(list(x_test), FLAGS.batch_size, 1, shuffle=False)

        # Collect the predictions here
        all_predictions = []

        for x_test_batch in batches:
            batch_predictions = sess.run(predictions, {input_x: x_test_batch, dropout_keep_prob: 1.0})
            all_predictions = np.concatenate([all_predictions, batch_predictions])

# Print accuracy if y_test is defined
if y_test is not None:
    correct_predictions = float(sum(all_predictions == y_test))
    print("Total number of test examples: {}".format(len(y_test)))
    print("Accuracy: {:g}".format(correct_predictions/float(len(y_test))))

# Save the evaluation to a csv
predictions_human_readable = np.column_stack((np.array(x_raw), all_predictions))
out_path = os.path.join(FLAGS.checkpoint_dir, "..", "prediction.csv")
print("Saving evaluation to {0}".format(out_path))
with open(out_path, 'w') as f:
    csv.writer(f).writerows(predictions_human_readable)

import tensorflow as tf
import numpy as np


class TextCNN(object):
    """
    A CNN for text classification.
    Uses an embedding layer, followed by a convolutional, max-pooling and softmax layer.
    """
    def __init__(
      self, sequence_length, num_classes, vocab_size,
      embedding_size, filter_sizes, num_filters, l2_reg_lambda=0.0):

        # Placeholders for input, output and dropout
        self.input_x = tf.placeholder(tf.int32, [None, sequence_length], name="input_x")
        self.input_y = tf.placeholder(tf.float32, [None, num_classes], name="input_y")
        self.dropout_keep_prob = tf.placeholder(tf.float32, name="dropout_keep_prob")

        # Keeping track of l2 regularization loss (optional)
        l2_loss = tf.constant(0.0)

        # Embedding layer
        with tf.device('/cpu:0'), tf.name_scope("embedding"):
            self.W = tf.Variable(
                tf.random_uniform([vocab_size, embedding_size], -1.0, 1.0),
                name="W")
            self.embedded_chars = tf.nn.embedding_lookup(self.W, self.input_x)
            self.embedded_chars_expanded = tf.expand_dims(self.embedded_chars, -1)

        # Create a convolution + maxpool layer for each filter size
        pooled_outputs = []
        for i, filter_size in enumerate(filter_sizes):
            with tf.name_scope("conv-maxpool-%s" % filter_size):
                # Convolution Layer
                filter_shape = [filter_size, embedding_size, 1, num_filters]
                W = tf.Variable(tf.truncated_normal(filter_shape, stddev=0.1), name="W")
                b = tf.Variable(tf.constant(0.1, shape=[num_filters]), name="b")
                conv = tf.nn.conv2d(
                    self.embedded_chars_expanded,
                    W,
                    strides=[1, 1, 1, 1],
                    padding="VALID",
                    name="conv")
                # Apply nonlinearity
                h = tf.nn.relu(tf.nn.bias_add(conv, b), name="relu")
                # Maxpooling over the outputs
                pooled = tf.nn.max_pool(
                    h,
                    ksize=[1, sequence_length - filter_size + 1, 1, 1],
                    strides=[1, 1, 1, 1],
                    padding='VALID',
                    name="pool")
                pooled_outputs.append(pooled)

        # Combine all the pooled features
        num_filters_total = num_filters * len(filter_sizes)
        #self.h_pool = tf.concat(pooled_outputs, 3)
        self.h_pool = tf.concat(pooled_outputs,3)
        self.h_pool_flat = tf.reshape(self.h_pool, [-1, num_filters_total])

        # Add dropout
        with tf.name_scope("dropout"):
            self.h_drop = tf.nn.dropout(self.h_pool_flat, self.dropout_keep_prob)

        # Final (unnormalized) scores and predictions
        with tf.name_scope("output"):
            W = tf.get_variable(
                "W",
                shape=[num_filters_total, num_classes],
                initializer=tf.contrib.layers.xavier_initializer())
            b = tf.Variable(tf.constant(0.1, shape=[num_classes]), name="b")
            l2_loss += tf.nn.l2_loss(W)
            l2_loss += tf.nn.l2_loss(b)
            self.scores = tf.nn.xw_plus_b(self.h_drop, W, b, name="scores")
            self.predictions = tf.argmax(self.scores, 1, name="predictions")

        # CalculateMean cross-entropy loss
        with tf.name_scope("loss"):
            losses = tf.nn.softmax_cross_entropy_with_logits(logits=self.scores, labels=self.input_y)
            self.loss = tf.reduce_mean(losses) + l2_reg_lambda * l2_loss

        # Accuracy
        with tf.name_scope("accuracy"):
            correct_predictions = tf.equal(self.predictions, tf.argmax(self.input_y, 1))
            self.accuracy = tf.reduce_mean(tf.cast(correct_predictions, "float"), name="accuracy")

接下来是训练阶段：

#! /usr/bin/env python

import tensorflow as tf
import numpy as np
import os
import time
import datetime
import data_helpers
from text_cnn import TextCNN
from tensorflow.contrib import learn

# Parameters
# ==================================================

# Data loading params
tf.flags.DEFINE_float("dev_sample_percentage", .1, "Percentage of the training data to use for validation")
tf.flags.DEFINE_string("positive_data_file", "./data/rt-polaritydata/rt-polarity.pos", "Data source for the positive data.")
tf.flags.DEFINE_string("negative_data_file", "./data/rt-polaritydata/rt-polarity.neg", "Data source for the negative data.")

# Model Hyperparameters
tf.flags.DEFINE_integer("embedding_dim", 128, "Dimensionality of character embedding (default: 128)")
tf.flags.DEFINE_string("filter_sizes", "3,4,5", "Comma-separated filter sizes (default: '3,4,5')")
tf.flags.DEFINE_integer("num_filters", 128, "Number of filters per filter size (default: 128)")
tf.flags.DEFINE_float("dropout_keep_prob", 0.5, "Dropout keep probability (default: 0.5)")
tf.flags.DEFINE_float("l2_reg_lambda", 0.0, "L2 regularization lambda (default: 0.0)")

tf.app.flags.DEFINE_string('f', '', 'kernel')

# Training parameters
tf.flags.DEFINE_integer("batch_size", 64, "Batch Size (default: 64)")
tf.flags.DEFINE_integer("num_epochs", 200, "Number of training epochs (default: 200)")
tf.flags.DEFINE_integer("evaluate_every", 100, "Evaluate model on dev set after this many steps (default: 100)")
tf.flags.DEFINE_integer("checkpoint_every", 100, "Save model after this many steps (default: 100)")
tf.flags.DEFINE_integer("num_checkpoints", 5, "Number of checkpoints to store (default: 5)")
# Misc Parameters
tf.flags.DEFINE_boolean("allow_soft_placement", True, "Allow device soft device placement")
tf.flags.DEFINE_boolean("log_device_placement", False, "Log placement of ops on devices")

FLAGS = tf.flags.FLAGS
FLAGS.flag_values_dict()
print("\nParameters:")
for attr, value in sorted(FLAGS.__flags.items()):
    print("{}={}".format(attr.upper(), value))
print("")


# Data Preparation
# ==================================================

# Load data
print("Loading data...")
x_text, y = data_helpers.load_data_and_labels(FLAGS.positive_data_file, FLAGS.negative_data_file)

# Build vocabulary
max_document_length = max([len(x.split(" ")) for x in x_text])
vocab_processor = learn.preprocessing.VocabularyProcessor(max_document_length)
x = np.array(list(vocab_processor.fit_transform(x_text)))

# Randomly shuffle data
np.random.seed(10)
shuffle_indices = np.random.permutation(np.arange(len(y)))
x_shuffled = x[shuffle_indices]
y_shuffled = y[shuffle_indices]

# Split train/test set
# TODO: This is very crude, should use cross-validation
dev_sample_index = -1 * int(FLAGS.dev_sample_percentage * float(len(y)))
x_train, x_dev = x_shuffled[:dev_sample_index], x_shuffled[dev_sample_index:]
y_train, y_dev = y_shuffled[:dev_sample_index], y_shuffled[dev_sample_index:]
print("Vocabulary Size: {:d}".format(len(vocab_processor.vocabulary_)))
print("Train/Dev split: {:d}/{:d}".format(len(y_train), len(y_dev)))


# Training
# ==================================================

with tf.Graph().as_default():
    session_conf = tf.ConfigProto(
      allow_soft_placement=FLAGS.allow_soft_placement,
      log_device_placement=FLAGS.log_device_placement)
    sess = tf.Session(config=session_conf)
    with sess.as_default():
        cnn = TextCNN(
            sequence_length=x_train.shape[1],
            num_classes=y_train.shape[1],
            vocab_size=len(vocab_processor.vocabulary_),
            embedding_size=FLAGS.embedding_dim,
            filter_sizes=list(map(int, FLAGS.filter_sizes.split(","))),
            num_filters=FLAGS.num_filters,
            l2_reg_lambda=FLAGS.l2_reg_lambda)

        # Define Training procedure
        global_step = tf.Variable(0, name="global_step", trainable=False)
        optimizer = tf.train.AdamOptimizer(1e-3)
        grads_and_vars = optimizer.compute_gradients(cnn.loss)
        train_op = optimizer.apply_gradients(grads_and_vars, global_step=global_step)

        # Keep track of gradient values and sparsity (optional)
        grad_summaries = []
        for g, v in grads_and_vars:
            if g is not None:
                grad_hist_summary = tf.summary.histogram("{}/grad/hist".format(v.name), g)
                sparsity_summary = tf.summary.scalar("{}/grad/sparsity".format(v.name), tf.nn.zero_fraction(g))
                grad_summaries.append(grad_hist_summary)
                grad_summaries.append(sparsity_summary)
        grad_summaries_merged = tf.summary.merge(grad_summaries)

        # Output directory for models and summaries
        timestamp = str(int(time.time()))
        out_dir = os.path.abspath(os.path.join(os.path.curdir, "runs", timestamp))
        print("Writing to {}\n".format(out_dir))

        # Summaries for loss and accuracy
        loss_summary = tf.summary.scalar("loss", cnn.loss)
        acc_summary = tf.summary.scalar("accuracy", cnn.accuracy)

        # Train Summaries
        train_summary_op = tf.summary.merge([loss_summary, acc_summary, grad_summaries_merged])
        train_summary_dir = os.path.join(out_dir, "summaries", "train")
        train_summary_writer = tf.summary.FileWriter(train_summary_dir, sess.graph)

        # Dev summaries
        dev_summary_op = tf.summary.merge([loss_summary, acc_summary])
        dev_summary_dir = os.path.join(out_dir, "summaries", "dev")
        dev_summary_writer = tf.summary.FileWriter(dev_summary_dir, sess.graph)

        # Checkpoint directory. Tensorflow assumes this directory already exists so we need to create it
        checkpoint_dir = os.path.abspath(os.path.join(out_dir, "checkpoints"))
        checkpoint_prefix = os.path.join(checkpoint_dir, "model")
        if not os.path.exists(checkpoint_dir):
            os.makedirs(checkpoint_dir)
        saver = tf.train.Saver(tf.global_variables(), max_to_keep=FLAGS.num_checkpoints)

        # Write vocabulary
        vocab_processor.save(os.path.join(out_dir, "vocab"))

        # Initialize all variables
        sess.run(tf.global_variables_initializer())

        def train_step(x_batch, y_batch):
            """
            A single training step
            """
            feed_dict = {
              cnn.input_x: x_batch,
              cnn.input_y: y_batch,
              cnn.dropout_keep_prob: FLAGS.dropout_keep_prob
            }
            _, step, summaries, loss, accuracy = sess.run(
                [train_op, global_step, train_summary_op, cnn.loss, cnn.accuracy],
                feed_dict)
            time_str = datetime.datetime.now().isoformat()
            print("{}: step {}, loss {:g}, acc {:g}".format(time_str, step, loss, accuracy))
            train_summary_writer.add_summary(summaries, step)

        def dev_step(x_batch, y_batch, writer=None):
            """
            Evaluates model on a dev set
            """
            feed_dict = {
              cnn.input_x: x_batch,
              cnn.input_y: y_batch,
              cnn.dropout_keep_prob: 1.0
            }
            step, summaries, loss, accuracy = sess.run(
                [global_step, dev_summary_op, cnn.loss, cnn.accuracy],
                feed_dict)
            time_str = datetime.datetime.now().isoformat()
            print("{}: step {}, loss {:g}, acc {:g}".format(time_str, step, loss, accuracy))
            if writer:
                writer.add_summary(summaries, step)

        # Generate batches
        batches = data_helpers.batch_iter(
            list(zip(x_train, y_train)), FLAGS.batch_size, FLAGS.num_epochs)
        # Training loop. For each batch...
        for batch in batches:
            x_batch, y_batch = zip(*batch)
            train_step(x_batch, y_batch)
            current_step = tf.train.global_step(sess, global_step)
            if current_step % FLAGS.evaluate_every == 0:
                print("\nEvaluation:")
                dev_step(x_dev, y_dev, writer=dev_summary_writer)
                print("")
            if current_step % FLAGS.checkpoint_every == 0:
                path = saver.save(sess, './', global_step=current_step)
                print("Saved model checkpoint to {}\n".format(path))

效果展示：

Parameters:
ALLOW_SOFT_PLACEMENT=<absl.flags._flag.BooleanFlag object at 0x000000000CB90CF8>
BATCH_SIZE=<absl.flags._flag.Flag object at 0x000000000CB90AC8>
CHECKPOINT_EVERY=<absl.flags._flag.Flag object at 0x000000000CB90CC0>
DEV_SAMPLE_PERCENTAGE=<absl.flags._flag.Flag object at 0x0000000004F07710>
DROPOUT_KEEP_PROB=<absl.flags._flag.Flag object at 0x000000000CB908D0>
EMBEDDING_DIM=<absl.flags._flag.Flag object at 0x000000000CB906D8>
EVALUATE_EVERY=<absl.flags._flag.Flag object at 0x000000000CB90C18>
F=<absl.flags._flag.Flag object at 0x000000000CB90A20>
FILTER_SIZES=<absl.flags._flag.Flag object at 0x000000000CB90780>
L2_REG_LAMBDA=<absl.flags._flag.Flag object at 0x000000000CB90978>
LOG_DEVICE_PLACEMENT=<absl.flags._flag.BooleanFlag object at 0x000000000CB90DA0>
NEGATIVE_DATA_FILE=<absl.flags._flag.Flag object at 0x000000000BDDF438>
NUM_CHECKPOINTS=<absl.flags._flag.Flag object at 0x000000000CB90D68>
NUM_EPOCHS=<absl.flags._flag.Flag object at 0x000000000CB90B70>
NUM_FILTERS=<absl.flags._flag.Flag object at 0x000000000CB90828>
POSITIVE_DATA_FILE=<absl.flags._flag.Flag object at 0x000000000BDDF3C8>

Loading data...
WARNING:tensorflow:From <ipython-input-1-bbb57832f2ce>:56: VocabularyProcessor.__init__ (from tensorflow.contrib.learn.python.learn.preprocessing.text) is deprecated and will be removed in a future version.
Instructions for updating:
Please use tensorflow/transform or tf.data.
WARNING:tensorflow:From D:\anaconda\envs\tensorflow\lib\site-packages\tensorflow\contrib\learn\python\learn\preprocessing\text.py:154: CategoricalVocabulary.__init__ (from tensorflow.contrib.learn.python.learn.preprocessing.categorical_vocabulary) is deprecated and will be removed in a future version.
Instructions for updating:
Please use tensorflow/transform or tf.data.
WARNING:tensorflow:From D:\anaconda\envs\tensorflow\lib\site-packages\tensorflow\contrib\learn\python\learn\preprocessing\text.py:170: tokenizer (from tensorflow.contrib.learn.python.learn.preprocessing.text) is deprecated and will be removed in a future version.
Instructions for updating:
Please use tensorflow/transform or tf.data.
Vocabulary Size: 18758
Train/Dev split: 9596/1066
WARNING:tensorflow:From C:\Users\Administrator\Desktop\text_cnn.py:79: 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}.

INFO:tensorflow:Summary name embedding/W:0/grad/hist is illegal; using embedding/W_0/grad/hist instead.
INFO:tensorflow:Summary name embedding/W:0/grad/sparsity is illegal; using embedding/W_0/grad/sparsity instead.
INFO:tensorflow:Summary name conv-maxpool-3/W:0/grad/hist is illegal; using conv-maxpool-3/W_0/grad/hist instead.
INFO:tensorflow:Summary name conv-maxpool-3/W:0/grad/sparsity is illegal; using conv-maxpool-3/W_0/grad/sparsity instead.
INFO:tensorflow:Summary name conv-maxpool-3/b:0/grad/hist is illegal; using conv-maxpool-3/b_0/grad/hist instead.
INFO:tensorflow:Summary name conv-maxpool-3/b:0/grad/sparsity is illegal; using conv-maxpool-3/b_0/grad/sparsity instead.
INFO:tensorflow:Summary name conv-maxpool-4/W:0/grad/hist is illegal; using conv-maxpool-4/W_0/grad/hist instead.
INFO:tensorflow:Summary name conv-maxpool-4/W:0/grad/sparsity is illegal; using conv-maxpool-4/W_0/grad/sparsity instead.
INFO:tensorflow:Summary name conv-maxpool-4/b:0/grad/hist is illegal; using conv-maxpool-4/b_0/grad/hist instead.
INFO:tensorflow:Summary name conv-maxpool-4/b:0/grad/sparsity is illegal; using conv-maxpool-4/b_0/grad/sparsity instead.
INFO:tensorflow:Summary name conv-maxpool-5/W:0/grad/hist is illegal; using conv-maxpool-5/W_0/grad/hist instead.
INFO:tensorflow:Summary name conv-maxpool-5/W:0/grad/sparsity is illegal; using conv-maxpool-5/W_0/grad/sparsity instead.
INFO:tensorflow:Summary name conv-maxpool-5/b:0/grad/hist is illegal; using conv-maxpool-5/b_0/grad/hist instead.
INFO:tensorflow:Summary name conv-maxpool-5/b:0/grad/sparsity is illegal; using conv-maxpool-5/b_0/grad/sparsity instead.
INFO:tensorflow:Summary name W:0/grad/hist is illegal; using W_0/grad/hist instead.
INFO:tensorflow:Summary name W:0/grad/sparsity is illegal; using W_0/grad/sparsity instead.
INFO:tensorflow:Summary name output/b:0/grad/hist is illegal; using output/b_0/grad/hist instead.
INFO:tensorflow:Summary name output/b:0/grad/sparsity is illegal; using output/b_0/grad/sparsity instead.
Writing to C:\Users\Administrator\Desktop\runs\1536738315

2018-09-12T15:45:19.915906: step 1, loss 2.49389, acc 0.4375
2018-09-12T15:45:20.265926: step 2, loss 1.79032, acc 0.53125
2018-09-12T15:45:20.564943: step 3, loss 2.14735, acc 0.4375
2018-09-12T15:45:20.908963: step 4, loss 1.4538, acc 0.53125
2018-09-12T15:45:21.233982: step 5, loss 2.09522, acc 0.546875
2018-09-12T15:45:21.547000: step 6, loss 1.6122, acc 0.515625
2018-09-12T15:45:21.883019: step 7, loss 1.7609, acc 0.5625
2018-09-12T15:45:22.201037: step 8, loss 2.31901, acc 0.40625
2018-09-12T15:45:22.543057: step 9, loss 1.61211, acc 0.546875
2018-09-12T15:45:22.969081: step 10, loss 2.31761, acc 0.390625
2018-09-12T15:45:23.376104: step 11, loss 1.6651, acc 0.546875
2018-09-12T15:45:23.835131: step 12, loss 2.12476, acc 0.515625
2018-09-12T15:45:24.247154: step 13, loss 1.81063, acc 0.515625
2018-09-12T15:45:24.580173: step 14, loss 2.00943, acc 0.53125
2018-09-12T15:45:24.899191: step 15, loss 2.44759, acc 0.40625
2018-09-12T15:45:25.220210: step 16, loss 2.05808, acc 0.5
2018-09-12T15:45:25.547228: step 17, loss 1.72565, acc 0.515625
2018-09-12T15:45:25.932250: step 18, loss 1.9766, acc 0.5625
2018-09-12T15:45:26.248269: step 19, loss 2.1489, acc 0.40625
2018-09-12T15:45:26.568287: step 20, loss 1.8569, acc 0.53125
2018-09-12T15:45:26.901306: step 21, loss 1.9758, acc 0.53125
2018-09-12T15:45:27.213324: step 22, loss 1.64478, acc 0.6875
2018-09-12T15:45:27.577345: step 23, loss 1.85216, acc 0.546875
2018-09-12T15:45:27.892363: step 24, loss 1.83535, acc 0.515625
2018-09-12T15:45:28.206381: step 25, loss 1.36567, acc 0.5625
2018-09-12T15:45:28.578402: step 26, loss 1.84147, acc 0.4375
2018-09-12T15:45:29.037027: step 27, loss 1.48389, acc 0.515625
2018-09-12T15:45:29.459051: step 28, loss 2.30555, acc 0.390625
2018-09-12T15:45:29.909077: step 29, loss 2.49438, acc 0.46875
2018-09-12T15:45:30.413106: step 30, loss 1.60412, acc 0.5
2018-09-12T15:45:30.972138: step 31, loss 2.20106, acc 0.4375
2018-09-12T15:45:31.541170: step 32, loss 1.77118, acc 0.546875
2018-09-12T15:45:32.113203: step 33, loss 1.69977, acc 0.515625
2018-09-12T15:45:32.608231: step 34, loss 1.92535, acc 0.484375
2018-09-12T15:45:33.129261: step 35, loss 2.1763, acc 0.4375
2018-09-12T15:45:33.681293: step 36, loss 1.42474, acc 0.59375
2018-09-12T15:45:34.186322: step 37, loss 2.18221, acc 0.359375
2018-09-12T15:45:34.694351: step 38, loss 1.21661, acc 0.625
2018-09-12T15:45:35.159377: step 39, loss 1.76056, acc 0.515625
2018-09-12T15:45:35.565401: step 40, loss 1.75754, acc 0.484375
2018-09-12T15:45:36.059429: step 41, loss 1.5117, acc 0.53125
2018-09-12T15:45:36.515455: step 42, loss 1.32369, acc 0.609375
2018-09-12T15:45:37.026484: step 43, loss 1.52577, acc 0.609375
2018-09-12T15:45:37.424507: step 44, loss 1.87095, acc 0.46875
2018-09-12T15:45:37.885533: step 45, loss 2.07323, acc