0
在此之前,我将输入图像转换为TFRecords文件。现在,我有我大部分来自教程收集和少许修改下面的方法:无法读取TensorFlow上的数据
def read_and_decode(filename_queue):
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
features = tf.parse_single_example(
serialized_example,
# Defaults are not specified since both keys are required.
features={
'image/encoded': tf.FixedLenFeature([], tf.string),
'image/class/label': tf.FixedLenFeature([], tf.int64),
})
image = tf.decode_raw(features['image/encoded'], tf.uint8)
label = tf.cast(features['image/class/label'], tf.int32)
reshaped_image = tf.reshape(image,[size[0], size[1], 3])
reshaped_image = tf.image.resize_images(reshaped_image, size[0], size[1], method = 0)
reshaped_image = tf.image.per_image_whitening(reshaped_image)
return reshaped_image, label
def inputs(train, batch_size, num_epochs):
filename = os.path.join(FLAGS.train_dir,
TRAIN_FILE if train else VALIDATION_FILE)
filename_queue = tf.train.string_input_producer(
[filename], num_epochs=num_epochs)
# Even when reading in multiple threads, share the filename
# queue.
image, label = read_and_decode(filename_queue)
# Shuffle the examples and collect them into batch_size batches.
# (Internally uses a RandomShuffleQueue.)
# We run this in two threads to avoid being a bottleneck.
images, sparse_labels = tf.train.shuffle_batch(
[image, label], batch_size=batch_size, num_threads=2,
capacity=1000 + 3 * batch_size,
# Ensures a minimum amount of shuffling of examples.
min_after_dequeue=1000)
return images, sparse_labels
但是,当我尝试调用上的IPython/Jupyter批次,过程永远不会结束(有似乎是一个循环)。我把这种方式:
batch_x, batch_y = inputs(True, 100,1)
print batch_x.eval()
谢谢你,现在我得到以下警告:ERROR:tensorflow:异常在QueueRunner:试图使用未初始化值input_producer/limit_epochs /时代 \t [节点:input_producer/limit_epochs/CountUpTo = CountUpTo [T = DT_INT64,_class = [“loc:@ input_producer/limit_epochs/epochs”],limit = 1000,_device =“/ job:localhost/replica:0/task:0/cpu:0”] (input_producer/limit_epochs /时期)]]。你知道什么可能导致它? – Kevin
我用另一张丢失的样板更新了问题。你需要调用'tf.initialize_all_variables.run()'(或'sess.run(tf.initialize_all_variables())')。如果这不起作用(取决于版本),您可能还需要添加'tf.initialize_local_variables()。run()'。 – mrry