Tensorflow MNIST TFRecord

Question

我該如何改變MNIST教程使用TFRecords而不是教程從網上下載的奇怪格式？

我以前build_image_data.py從成立之初模型來創建一個包含200×200的RGB圖像我TFRecords並打算培養這個在1080Ti，但我不能找到如何加載TFRecords任何好的例子，並將它們送入卷積神經網絡。

Answer 1

我做了一件類似的事情，你打算做。我也採用了相同的腳本來構建圖像數據。我的代碼讀取數據和訓練它是

import tensorflow as tf 

height = 28 
width = 28 

tfrecords_train_filename = 'train-00000-of-00001' 
tfrecords_test_filename = 'test-00000-of-00001' 


def read_and_decode(filename_queue): 
    reader = tf.TFRecordReader() 

    _, serialized_example = reader.read(filename_queue) 

    features = tf.parse_single_example(
     serialized_example, 
     features={ 
      'image/height': tf.FixedLenFeature([], tf.int64), 
      'image/width': tf.FixedLenFeature([], tf.int64), 
      'image/colorspace': tf.FixedLenFeature([], dtype=tf.string, default_value=''), 
      'image/channels': tf.FixedLenFeature([], tf.int64), 
      'image/class/label': tf.FixedLenFeature([], tf.int64), 
      'image/class/text': tf.FixedLenFeature([], dtype=tf.string, default_value=''), 
      'image/format': tf.FixedLenFeature([], dtype=tf.string, default_value=''), 
      'image/filename': tf.FixedLenFeature([], dtype=tf.string, default_value=''), 
      'image/encoded': tf.FixedLenFeature([], dtype=tf.string, default_value='') 
     }) 

    image_buffer = features['image/encoded'] 
    image_label = tf.cast(features['image/class/label'], tf.int32) 

    # Decode the jpeg 
    with tf.name_scope('decode_jpeg', [image_buffer], None): 
     # decode 
     image = tf.image.decode_jpeg(image_buffer, channels=3) 

     # and convert to single precision data type 
     image = tf.image.convert_image_dtype(image, dtype=tf.float32) 
     image = tf.image.rgb_to_grayscale(image) 

    image_shape = tf.stack([height, width, 1]) 
    image = tf.reshape(image, image_shape) 

    return image, image_label 


def inputs(filename, batch_size, num_epochs): 
    if not num_epochs: num_epochs = None 

    with tf.name_scope('input'): 
     filename_queue = tf.train.string_input_producer([filename], num_epochs=None) 
     image, label = read_and_decode(filename_queue) 

     # Shuffle the examples and collect them into batch_size batches. 
     images, sparse_labels = tf.train.shuffle_batch(
      [image, label], batch_size=batch_size, num_threads=2, 
      capacity=1000 + 3 * batch_size, 
      min_after_dequeue=1000) 

     return images, sparse_labels 

image, label = inputs(filename=tfrecords_train_filename, batch_size=200, num_epochs=None) 
image = tf.reshape(image, [-1, 784]) 
label = tf.one_hot(label - 1, 10) 

# Create the model 
x = tf.placeholder(tf.float32, [None, 784]) 
W = tf.Variable(tf.zeros([784, 10])) 
b = tf.Variable(tf.zeros([10])) 
y = tf.matmul(x, W) + b 
y_ = tf.placeholder(tf.float32, [None, 10]) 

cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y)) 

train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy) 

with tf.Session() as sess: 
    sess.run(tf.global_variables_initializer()) 

    coord = tf.train.Coordinator() 
    threads = tf.train.start_queue_runners(coord=coord) 

    correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1)) 
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) 

    for i in range(1000): 
     img, lbl = sess.run([image, label]) 
     sess.run(train_step, feed_dict={x: img, y_: lbl}) 

    img, lbl = sess.run([image, label]) 
    print(sess.run(accuracy, feed_dict={x: img, y_: lbl})) 

    coord.request_stop() 
    coord.join(threads) 

這是一個超級簡單的分類mnist模型。不過，我認爲這也是如何使用TFRecord文件進行訓練的一個可擴展的答案。它尚未考慮到評估數據，因爲這需要更多的協調工作。