Question

我想用张量＆＃34;图像＆＃34;来馈送CNN。当占位符is_training为True时，我希望此张量包含来自训练集的图像（具有FIXED大小），否则我希望它包含来自测试集的图像（非固定大小）。

这是必要的，因为在训练中我从训练图像中采取随机固定裁剪，而在测试中我想要执行密集评估并将整个图像馈送到网络内（它完全卷积，因此它将接受它们）< / p>

当前的NOT WORKING方法是创建两个不同的迭代器，并尝试在session.run中选择tf.cond的训练/测试输入（images，{is_training：True / False}）。

问题在于评估迭代器。训练和测试数据集也有不同的大小，所以我不能迭代它们直到最后。有没有办法让这项工作？或者以更聪明的方式重写它？

我已经看到了一些有关此问题的答案，但他们总是使用tf.assign，它采用numpy数组并将其分配给张量。在这种情况下，我不能使用tf.assign，因为我已经有一个来自迭代器的张量。

我当前的代码就是这个。它只是检查张量的形状＆＃34;图像＆＃34;：

train_filenames, train_labels = list_images(args.train_dir)
val_filenames, val_labels = list_images(args.val_dir)

graph = tf.Graph()
with graph.as_default():

    # Preprocessing (for both training and validation):
    def _parse_function(filename, label):
        image_string = tf.read_file(filename)
        image_decoded = tf.image.decode_jpeg(image_string, channels=3)          
        image = tf.cast(image_decoded, tf.float32)

        return image, label

    # Preprocessing (for training)
    def training_preprocess(image, label):

        # Random flip and crop
        image = tf.image.random_flip_left_right(image)
        image = tf.random_crop(image, [args.crop,args.crop, 3])

        return image, label

    # Preprocessing (for validation)
    def val_preprocess(image, label):

        flipped_image = tf.image.flip_left_right(image)
        batch = tf.stack([image,flipped_image],axis=0)

        return batch, label

    # Training dataset
    train_filenames = tf.constant(train_filenames)
    train_labels = tf.constant(train_labels)
    train_dataset = tf.contrib.data.Dataset.from_tensor_slices((train_filenames, train_labels))
    train_dataset = train_dataset.map(_parse_function,num_threads=args.num_workers, output_buffer_size=args.batch_size)
    train_dataset = train_dataset.map(training_preprocess,num_threads=args.num_workers, output_buffer_size=args.batch_size)
    train_dataset = train_dataset.shuffle(buffer_size=10000) 
    batched_train_dataset = train_dataset.batch(args.batch_size)

    # Validation dataset
    val_filenames = tf.constant(val_filenames)
    val_labels = tf.constant(val_labels)
    val_dataset = tf.contrib.data.Dataset.from_tensor_slices((val_filenames, val_labels))
    val_dataset = val_dataset.map(_parse_function,num_threads=1, output_buffer_size=1)
    val_dataset = val_dataset.map(val_preprocess,num_threads=1, output_buffer_size=1)

    train_iterator = tf.contrib.data.Iterator.from_structure(batched_train_dataset.output_types,batched_train_dataset.output_shapes)
    val_iterator = tf.contrib.data.Iterator.from_structure(val_dataset.output_types,val_dataset.output_shapes)

    train_images, train_labels = train_iterator.get_next()
    val_images, val_labels = val_iterator.get_next()

    train_init_op = train_iterator.make_initializer(batched_train_dataset)
    val_init_op = val_iterator.make_initializer(val_dataset)

    # Indicates whether we are in training or in test mode
    is_training = tf.placeholder(tf.bool)

    def f_true():
        with tf.control_dependencies([tf.identity(train_images)]):
            return tf.identity(train_images)

    def f_false():
        return val_images

    images = tf.cond(is_training,f_true,f_false)

    num_images = images.shape

    with tf.Session(graph=graph) as sess:

        sess.run(train_init_op)
        #sess.run(val_init_op)

        img = sess.run(images,{is_training:True})
        print(img.shape)

问题在于，当我只想使用训练迭代器时，我会对该行进行注释以初始化val_init_op但是存在以下错误：

FailedPreconditionError (see above for traceback): GetNext() failed because the iterator has not been initialized. Ensure that you have run the initializer operation for this iterator before getting the next element.
 [[Node: IteratorGetNext_1 = IteratorGetNext[output_shapes=[[2,?,?,3], []], output_types=[DT_FLOAT, DT_INT32], _device="/job:localhost/replica:0/task:0/cpu:0"](Iterator_1)]]

如果我不评论该行，一切都按预期工作，当is_training为真时，我得到训练图像，当is_training为False时，我得到验证图像。问题是两个迭代器都需要初始化，当我评估其中一个时，另一个也会递增。因为正如我所说，它们的大小不同会导致问题。

我希望有办法解决它！提前致谢

Answer 1

诀窍是在iterator.get_next()和f_true()函数内调用f_false()

：

def f_true(): train_images, _ = train_iterator.get_next() return train_images def f_false(): val_images, _ = val_iterator.get_next() return val_images images = tf.cond(is_training, f_true, f_false)

同样的建议适用于任何具有副作用的TensorFlow操作，例如分配给变量：如果您希望有条件地发生副作用，则必须在传递给tf.cond()的相应分支函数内创建op。

如何使用Tensorflow的tf.cond（）和两个不同的数据集迭代器而不重复两者？

1 个答案: