Tensorflow The same training accuracy continues

Question

I'm stuck on CNN model on Tensorflow. My code as below.

Libraries

# -*- coding: utf-8 -*-
import tensorflow as tf
import time
import json
import numpy as np
import matplotlib.pyplot as plt
import random
import multiprocessing as mp
import glob
import os

Model

def inference(images_placeholder, keep_prob):

    def weight_variable(shape):
        initial = tf.truncated_normal(shape, stddev=0.1)
        return tf.Variable(initial)

    def bias_variable(shape):
        initial = tf.constant(0.1, shape=shape)
        return tf.Variable(initial)

    # convolution
    def conv2d(x, W):
        return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

    # X2 pooling
    def max_pool_2x128(x):
        return tf.nn.max_pool(x, ksize=[1, 2, 1, 1],strides=[1, 2, 1, 1], padding='VALID')
    # X4 pooling
    def max_pool_4x128(x):
        return tf.nn.max_pool(x, ksize=[1, 4, 1, 1],strides=[1, 4, 1, 1], padding='VALID')

    x_image = tf.reshape(images_placeholder, [-1,599,1,128])

    #1st conv
    with tf.name_scope('conv1') as scope:
        W_conv1 = weight_variable([4, 1, 128, 256])
        b_conv1 = bias_variable([256])

        print "image変形後のshape"
        print tf.Tensor.get_shape(x_image)
        print "conv1の形"
        print tf.Tensor.get_shape(conv2d(x_image, W_conv1))

        h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)

    #1st pooling X4
    with tf.name_scope('pool1') as scope:
        h_pool1 = max_pool_4x128(h_conv1)
        print "h_pool1の形"
        print tf.Tensor.get_shape(h_pool1)

    #2nd conv
    with tf.name_scope('conv2') as scope:
        W_conv2 = weight_variable([4, 1, 256, 256])
        b_conv2 = bias_variable([256])
        h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)

    #2nd pooling X2
    with tf.name_scope('pool2') as scope:
        h_pool2 = max_pool_2x128(h_conv2)
        print "h_pool2の形"
        print tf.Tensor.get_shape(h_pool2)

    #3rd conv
    with tf.name_scope('conv3') as scope:
        W_conv3 = weight_variable([4, 1, 256, 512])
        b_conv3 = bias_variable([512])
        h_conv3 = tf.nn.relu(conv2d(h_pool2, W_conv3) + b_conv3)

    #3rd pooling X2
    with tf.name_scope('pool3') as scope:
        h_pool3 = max_pool_2x128(h_conv3)
        print "h_pool3の形"
        print tf.Tensor.get_shape(h_pool3)

    #flatten + 1st fully connected
    with tf.name_scope('fc1') as scope:
        W_fc1 = weight_variable([37 * 1 * 512, 2048])
        b_fc1 = bias_variable([2048])
        h_pool3_flat = tf.reshape(h_pool3, [-1, 37 * 1 * 512])
        h_fc1 = tf.nn.relu(tf.matmul(h_pool3_flat, W_fc1) + b_fc1)
        #ドロップ層の設定
        h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

    #2nd fully connected
    with tf.name_scope('fc2') as scope:
        W_fc2 = weight_variable([2048, NUM_CLASSES])
        b_fc2 = bias_variable([NUM_CLASSES])

    #softmax output
    with tf.name_scope('softmax') as scope:
        y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

    return y_conv

Loss

def loss(logits, labels):
    # cross entropy
    cross_entropy = -tf.reduce_sum(labels*tf.log(tf.clip_by_value(logits,1e-10,1.0)))
    # TensorBoard
    tf.scalar_summary("cross_entropy", cross_entropy)
    return cross_entropy

Training

def training(loss, learning_rate):
    train_step = tf.train.AdamOptimizer(learning_rate).minimize(loss)
    return train_step

Accuracy

def accuracy(logits, labels):
    correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(labels, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
    tf.scalar_summary("accuracy", accuracy)
    return accuracy

Main

if __name__ == '__main__':

    flags = tf.app.flags
    FLAGS = flags.FLAGS

    flags.DEFINE_string('train_dir', '/tmp/data', 'Directory to put the training data.')
    flags.DEFINE_integer('max_steps', , 'Number of steps to run trainer.')
    flags.DEFINE_integer('batch_size', 10, 'Batch size'
                         'Must divide evenly into the dataset sizes.')
    flags.DEFINE_float('learning_rate', 1e-4, 'Initial learning rate.')

    #num output
    NUM_CLASSES = 5
    #num frame
    IMAGE_SIZE = 599
    #tensor shape
    IMAGE_PIXELS = IMAGE_SIZE*1*128

    ##################
    #modify the data #
    ##################

    #number of training data
    train_num = 70
    #loading data limit
    data_limit = 100

    flatten_data = []
    flatten_label = []

    # データの整形
    filenames = glob.glob(os.path.join('/Users/kosukefukui/Qosmo/WASABEAT/song_features/*.json'))
    filenames = filenames[0:data_limit]
    print "----loading data---"
    for file_path in filenames:
        data = json.load(open(file_path))
        data = np.array(data)

        for_flat = np.array(data)
        assert for_flat.flatten().shape == (IMAGE_PIXELS,)
        flatten_data.append(for_flat.flatten().tolist())

    # ラベルの整形
    f2 = open("id_information.txt")
    print "---loading labels----"

    for line in f2:
        line = line.rstrip()
        l = line.split(",")
        tmp = np.zeros(NUM_CLASSES)
        tmp[int(l[4])] = 1
        flatten_label.append(tmp)

    flatten_label = flatten_label[0:data_limit]

    print "データ数 %s" % len(flatten_data)
    print "ラベルデータ数 %s" % len(flatten_label)

    #train data
    train_image = np.asarray(flatten_data[0:train_num], dtype=np.float32)
    train_label = np.asarray(flatten_label[0:train_num],dtype=np.float32)

    print "訓練データ数 %s" % len(train_image)

    #test data
    test_image = np.asarray(flatten_data[train_num:data_limit], dtype=np.float32)
    test_label = np.asarray(flatten_label[train_num:data_limit],dtype=np.float32)

    print "テストデータ数 %s" % len(test_image)

    print "599×128 = "
    print len(train_image[0])

    f2.close()

    if 1==1:
        # Image Tensor
        images_placeholder = tf.placeholder("float", shape=(None, IMAGE_PIXELS))
        # Label Tensor
        labels_placeholder = tf.placeholder("float", shape=(None, NUM_CLASSES))
        # dropout Tensor
        keep_prob = tf.placeholder("float")

        # construct model
        logits = inference(images_placeholder, keep_prob)
        # calculate loss
        loss_value = loss(logits, labels_placeholder)
        # training
        train_op = training(loss_value, FLAGS.learning_rate)
        # accuracy
        acc = accuracy(logits, labels_placeholder)

        saver = tf.train.Saver()
        sess = tf.Session()
        sess.run(tf.initialize_all_variables())
        # for TensorBoard
        summary_op = tf.merge_all_summaries()
        summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, sess.graph_def)

        # Training
        for step in range(FLAGS.max_steps):
            for i in range(len(train_image)/FLAGS.batch_size):
                # train for batch_size
                batch = FLAGS.batch_size*i
                sess.run(train_op, feed_dict={
                  images_placeholder: train_image[batch:batch+FLAGS.batch_size],
                  labels_placeholder: train_label[batch:batch+FLAGS.batch_size],
                  keep_prob: 0.5})

            # calculate accuracy at each step
            train_accuracy = sess.run(acc, feed_dict={
                images_placeholder: train_image,
                labels_placeholder: train_label,
                keep_prob: 1.0})
            print "step %d, training accuracy %g"%(step, train_accuracy)

            # add value for Tensorboard at each step
            summary_str = sess.run(summary_op, feed_dict={
                images_placeholder: train_image,
                labels_placeholder: train_label,
                keep_prob:1.0})
            summary_writer.add_summary(summary_str, step)

    # show accuracy for test data
    print "test accuracy %g"%sess.run(acc, feed_dict={
        images_placeholder: test_image,
        labels_placeholder: test_label,
        keep_prob: 1.0})
    # save the last model
    save_path = saver.save(sess, "model.ckpt")

However, I got the same training accuracy. How to fix this problem?

step 0, training accuracy 0.142857
step 1, training accuracy 0.142857
step 2, training accuracy 0.142857
step 3, training accuracy 0.142857
step 4, training accuracy 0.142857
step 5, training accuracy 0.142857
step 6, training accuracy 0.142857
step 7, training accuracy 0.142857
step 8, training accuracy 0.142857
step 9, training accuracy 0.142857
test accuracy 0.133333

I referred the following model and my tensorboard is as below.

Answer 1

Could it be that you are not minimizing the right tensor? You are minimizing cross_entropy, but should be cross_entropy_mean (accuracy in your code).

Basically with the following logic:

cross_entropy = tf.nn.softmax_cross_entropy_with_logits(
      logits, ground_truth_placeholder)

cross_entropy_mean = tf.reduce_mean(cross_entropy)

train_step = tf.train.GradientDescentOptimizer(FLAGS.learning_rate).minimize(
      cross_entropy_mean)