如何在使用可初始化迭代器时从tensorflow中的多个TFR记录中检索示例
我有多个名为:如何在使用可初始化迭代器时从tensorflow中的多个TFR记录中检索示例,tensorflow,tensorflow-datasets,Tensorflow,Tensorflow Datasets,我有多个名为:Train_DE_01.tfrecords到Train_DE_34.tfrecords;和Devel_DE_01.tfrecords到Devel_DE_14.tfrecords。因此,我有一个培训和验证数据集。我的目标是迭代tfrecords的示例,这样我可以从Train\u DE\u 01.tfrecords,从Train\u DE\u 02.tfrecords,检索到两个示例。。。和2Train\u DE_34.tfrecords。换句话说,当批大小为68时,我需要从每个tfr
Train_DE_01.tfrecords
到Train_DE_34.tfrecords
;和Devel_DE_01.tfrecords
到Devel_DE_14.tfrecords
。因此,我有一个培训和验证数据集。我的目标是迭代tfrecords的示例,这样我可以从Train\u DE\u 01.tfrecords
,从Train\u DE\u 02.tfrecords
,检索到两个示例。。。和2Train\u DE_34.tfrecords
。换句话说,当批大小为68时,我需要从每个tfrecord
文件中提取两个示例。在我的代码中,我使用了一个可初始化的迭代器,如下所示:
# file_name: This is a place_holder that will contain the name of the files of the tfrecords.
def load_sewa_data(file_name, batch_size):
with tf.name_scope('sewa_tf_records'):
dataset = tf.data.TFRecordDataset(file_name).map(_parse_sewa_example).batch(batch_size)
iterator = dataset.make_initializable_iterator(shared_name='sewa_iterator')
next_batch = iterator.get_next()
names, detected, arousal, valence, liking, istalkings, images = next_batch
print(names, detected, arousal, valence, liking, istalkings, images)
return names, detected, arousal, valence, liking, istalkings, images, iterator
def load_devel_sewa_tfrecords(filenames_dev, test_batch_size):
datasets_dev_iterators = []
with tf.name_scope('TFRecordsDevel'):
for file_name in filenames_dev:
dataset_dev = tf.data.TFRecordDataset(file_name).map(_parse_devel_function).batch(test_batch_size)
datasets_dev_iterators.append(dataset_dev)
dataset_dev_all = tf.data.Dataset.zip(tuple(datasets_dev_iterators))
return dataset_dev_all
def load_train_sewa_tfrecords(filenames_train, train_batch_size):
datasets_train_iterators = []
with tf.name_scope('TFRecordsTrain'):
for file_name in filenames_train:
dataset_train = tf.data.TFRecordDataset(file_name).map(_parse_train_function).batch(train_batch_size)
datasets_train_iterators.append(dataset_train)
dataset_train_all = tf.data.Dataset.zip(tuple(datasets_train_iterators))
return dataset_train_all
def load_sewa_dataset(filenames_train, train_batch_size, filenames_dev, test_batch_size):
dataset_train_all = load_train_sewa_tfrecords(filenames_train, train_batch_size)
dataset_dev_all = load_devel_sewa_tfrecords(filenames_dev, test_batch_size)
iterator = tf.data.Iterator.from_structure(dataset_train_all.output_types,
dataset_train_all.output_shapes)
training_init_op = iterator.make_initializer(dataset_train_all)
validation_init_op = iterator.make_initializer(dataset_dev_all)
with tf.name_scope('inputs'):
next_batch = iterator.get_next(name='next_batch')
names = []
detected = []
arousal = []
valence = []
liking = []
istalkings = []
images = []
# len(next_batch) is 34.
# len(n) is 7. Since we are extracting: name, detected, arousal, valence, liking, istalking and images...
# len(n[0 or 1 or 2 or ... or 6]) = is batch size.
for n in next_batch:
names.append(n[0])
detected.append(n[1])
arousal.append(n[2])
valence.append(n[3])
liking.append(n[4])
istalkings.append(n[5])
images.append(n[6])
names = tf.concat(names, axis=0, name='names')
detected = tf.concat(detected, axis=0, name='detected')
arousal = tf.concat(arousal, axis=0, name='arousal')
valence = tf.concat(valence, axis=0, name='valence')
liking = tf.concat(liking, axis=0, name='liking')
istalkings = tf.concat(istalkings, axis=0, name='istalkings')
images = tf.concat(images, axis=0, name='images')
return names, detected, arousal, valence, liking, istalkings, images, training_init_op, validation_init_op
def load_train_sewa_tfrecords(filenames_train, train_batch_size):
datasets_train_iterators = []
with tf.name_scope('TFRecordsTrain'):
for file_name in filenames_train:
dataset_train = tf.data.TFRecordDataset(file_name).map(_parse_train_function).batch(train_batch_size)
datasets_train_iterators.append(dataset_train)
dataset_train_all = tf.data.Dataset.zip(tuple(datasets_train_iterators))
iterator_train_all = dataset_train_all.make_initializable_iterator()
with tf.name_scope('inputs_train'):
next_batch = iterator_train_all.get_next(name='next_batch')
names = []
detected = []
arousal = []
valence = []
liking = []
istalkings = []
images = []
# len(next_batch) is 34.
# len(n) is 7. Since we are extracting: name, detected, arousal, valence, liking, istalking and images...
# len(n[0 or 1 or 2 or ... or 6]) = is batch size.
for n in next_batch:
names.append(n[0])
detected.append(n[1])
arousal.append(n[2])
valence.append(n[3])
liking.append(n[4])
istalkings.append(n[5])
images.append(n[6])
names = tf.concat(names, axis=0, name='names')
detected = tf.concat(detected, axis=0, name='detected')
arousal = tf.concat(arousal, axis=0, name='arousal')
valence = tf.concat(valence, axis=0, name='valence')
liking = tf.concat(liking, axis=0, name='liking')
istalkings = tf.concat(istalkings, axis=0, name='istalkings')
images = tf.concat(images, axis=0, name='images')
return names, detected, arousal, valence, liking, istalkings, images, iterator_train_all
使用sess.run()在会话中运行名称之后;我发现前68个示例是从Train_DE_01.tfrecords
获取的;然后,从同一个tfrecord中提取后续示例,直到使用Train_DE_01.tfrecords
中的所有示例
我已尝试将Dataset api的zip()函数与可重新初始化的迭代器一起使用,如下所示:
# file_name: This is a place_holder that will contain the name of the files of the tfrecords.
def load_sewa_data(file_name, batch_size):
with tf.name_scope('sewa_tf_records'):
dataset = tf.data.TFRecordDataset(file_name).map(_parse_sewa_example).batch(batch_size)
iterator = dataset.make_initializable_iterator(shared_name='sewa_iterator')
next_batch = iterator.get_next()
names, detected, arousal, valence, liking, istalkings, images = next_batch
print(names, detected, arousal, valence, liking, istalkings, images)
return names, detected, arousal, valence, liking, istalkings, images, iterator
def load_devel_sewa_tfrecords(filenames_dev, test_batch_size):
datasets_dev_iterators = []
with tf.name_scope('TFRecordsDevel'):
for file_name in filenames_dev:
dataset_dev = tf.data.TFRecordDataset(file_name).map(_parse_devel_function).batch(test_batch_size)
datasets_dev_iterators.append(dataset_dev)
dataset_dev_all = tf.data.Dataset.zip(tuple(datasets_dev_iterators))
return dataset_dev_all
def load_train_sewa_tfrecords(filenames_train, train_batch_size):
datasets_train_iterators = []
with tf.name_scope('TFRecordsTrain'):
for file_name in filenames_train:
dataset_train = tf.data.TFRecordDataset(file_name).map(_parse_train_function).batch(train_batch_size)
datasets_train_iterators.append(dataset_train)
dataset_train_all = tf.data.Dataset.zip(tuple(datasets_train_iterators))
return dataset_train_all
def load_sewa_dataset(filenames_train, train_batch_size, filenames_dev, test_batch_size):
dataset_train_all = load_train_sewa_tfrecords(filenames_train, train_batch_size)
dataset_dev_all = load_devel_sewa_tfrecords(filenames_dev, test_batch_size)
iterator = tf.data.Iterator.from_structure(dataset_train_all.output_types,
dataset_train_all.output_shapes)
training_init_op = iterator.make_initializer(dataset_train_all)
validation_init_op = iterator.make_initializer(dataset_dev_all)
with tf.name_scope('inputs'):
next_batch = iterator.get_next(name='next_batch')
names = []
detected = []
arousal = []
valence = []
liking = []
istalkings = []
images = []
# len(next_batch) is 34.
# len(n) is 7. Since we are extracting: name, detected, arousal, valence, liking, istalking and images...
# len(n[0 or 1 or 2 or ... or 6]) = is batch size.
for n in next_batch:
names.append(n[0])
detected.append(n[1])
arousal.append(n[2])
valence.append(n[3])
liking.append(n[4])
istalkings.append(n[5])
images.append(n[6])
names = tf.concat(names, axis=0, name='names')
detected = tf.concat(detected, axis=0, name='detected')
arousal = tf.concat(arousal, axis=0, name='arousal')
valence = tf.concat(valence, axis=0, name='valence')
liking = tf.concat(liking, axis=0, name='liking')
istalkings = tf.concat(istalkings, axis=0, name='istalkings')
images = tf.concat(images, axis=0, name='images')
return names, detected, arousal, valence, liking, istalkings, images, training_init_op, validation_init_op
def load_train_sewa_tfrecords(filenames_train, train_batch_size):
datasets_train_iterators = []
with tf.name_scope('TFRecordsTrain'):
for file_name in filenames_train:
dataset_train = tf.data.TFRecordDataset(file_name).map(_parse_train_function).batch(train_batch_size)
datasets_train_iterators.append(dataset_train)
dataset_train_all = tf.data.Dataset.zip(tuple(datasets_train_iterators))
iterator_train_all = dataset_train_all.make_initializable_iterator()
with tf.name_scope('inputs_train'):
next_batch = iterator_train_all.get_next(name='next_batch')
names = []
detected = []
arousal = []
valence = []
liking = []
istalkings = []
images = []
# len(next_batch) is 34.
# len(n) is 7. Since we are extracting: name, detected, arousal, valence, liking, istalking and images...
# len(n[0 or 1 or 2 or ... or 6]) = is batch size.
for n in next_batch:
names.append(n[0])
detected.append(n[1])
arousal.append(n[2])
valence.append(n[3])
liking.append(n[4])
istalkings.append(n[5])
images.append(n[6])
names = tf.concat(names, axis=0, name='names')
detected = tf.concat(detected, axis=0, name='detected')
arousal = tf.concat(arousal, axis=0, name='arousal')
valence = tf.concat(valence, axis=0, name='valence')
liking = tf.concat(liking, axis=0, name='liking')
istalkings = tf.concat(istalkings, axis=0, name='istalkings')
images = tf.concat(images, axis=0, name='images')
return names, detected, arousal, valence, liking, istalkings, images, iterator_train_all
现在,如果我尝试以下方法:
sess = tf.Session()
sess.run(training_init_op)
print(sess.run(names))
我得到了以下错误:
ValueError: The two structures don't have the same number of elements.
这是有意义的,因为训练文件的数量是34,而验证数据集的数量是14
我想知道我怎样才能实现心中的目标
非常感谢您的帮助 以下是我使用
tf.cond
找到的解决方法
为了从每个tfrecord
中检索2个示例;我使用了tf.Dataset.data
api的zip
方法,如下所示:
# file_name: This is a place_holder that will contain the name of the files of the tfrecords.
def load_sewa_data(file_name, batch_size):
with tf.name_scope('sewa_tf_records'):
dataset = tf.data.TFRecordDataset(file_name).map(_parse_sewa_example).batch(batch_size)
iterator = dataset.make_initializable_iterator(shared_name='sewa_iterator')
next_batch = iterator.get_next()
names, detected, arousal, valence, liking, istalkings, images = next_batch
print(names, detected, arousal, valence, liking, istalkings, images)
return names, detected, arousal, valence, liking, istalkings, images, iterator
def load_devel_sewa_tfrecords(filenames_dev, test_batch_size):
datasets_dev_iterators = []
with tf.name_scope('TFRecordsDevel'):
for file_name in filenames_dev:
dataset_dev = tf.data.TFRecordDataset(file_name).map(_parse_devel_function).batch(test_batch_size)
datasets_dev_iterators.append(dataset_dev)
dataset_dev_all = tf.data.Dataset.zip(tuple(datasets_dev_iterators))
return dataset_dev_all
def load_train_sewa_tfrecords(filenames_train, train_batch_size):
datasets_train_iterators = []
with tf.name_scope('TFRecordsTrain'):
for file_name in filenames_train:
dataset_train = tf.data.TFRecordDataset(file_name).map(_parse_train_function).batch(train_batch_size)
datasets_train_iterators.append(dataset_train)
dataset_train_all = tf.data.Dataset.zip(tuple(datasets_train_iterators))
return dataset_train_all
def load_sewa_dataset(filenames_train, train_batch_size, filenames_dev, test_batch_size):
dataset_train_all = load_train_sewa_tfrecords(filenames_train, train_batch_size)
dataset_dev_all = load_devel_sewa_tfrecords(filenames_dev, test_batch_size)
iterator = tf.data.Iterator.from_structure(dataset_train_all.output_types,
dataset_train_all.output_shapes)
training_init_op = iterator.make_initializer(dataset_train_all)
validation_init_op = iterator.make_initializer(dataset_dev_all)
with tf.name_scope('inputs'):
next_batch = iterator.get_next(name='next_batch')
names = []
detected = []
arousal = []
valence = []
liking = []
istalkings = []
images = []
# len(next_batch) is 34.
# len(n) is 7. Since we are extracting: name, detected, arousal, valence, liking, istalking and images...
# len(n[0 or 1 or 2 or ... or 6]) = is batch size.
for n in next_batch:
names.append(n[0])
detected.append(n[1])
arousal.append(n[2])
valence.append(n[3])
liking.append(n[4])
istalkings.append(n[5])
images.append(n[6])
names = tf.concat(names, axis=0, name='names')
detected = tf.concat(detected, axis=0, name='detected')
arousal = tf.concat(arousal, axis=0, name='arousal')
valence = tf.concat(valence, axis=0, name='valence')
liking = tf.concat(liking, axis=0, name='liking')
istalkings = tf.concat(istalkings, axis=0, name='istalkings')
images = tf.concat(images, axis=0, name='images')
return names, detected, arousal, valence, liking, istalkings, images, training_init_op, validation_init_op
def load_train_sewa_tfrecords(filenames_train, train_batch_size):
datasets_train_iterators = []
with tf.name_scope('TFRecordsTrain'):
for file_name in filenames_train:
dataset_train = tf.data.TFRecordDataset(file_name).map(_parse_train_function).batch(train_batch_size)
datasets_train_iterators.append(dataset_train)
dataset_train_all = tf.data.Dataset.zip(tuple(datasets_train_iterators))
iterator_train_all = dataset_train_all.make_initializable_iterator()
with tf.name_scope('inputs_train'):
next_batch = iterator_train_all.get_next(name='next_batch')
names = []
detected = []
arousal = []
valence = []
liking = []
istalkings = []
images = []
# len(next_batch) is 34.
# len(n) is 7. Since we are extracting: name, detected, arousal, valence, liking, istalking and images...
# len(n[0 or 1 or 2 or ... or 6]) = is batch size.
for n in next_batch:
names.append(n[0])
detected.append(n[1])
arousal.append(n[2])
valence.append(n[3])
liking.append(n[4])
istalkings.append(n[5])
images.append(n[6])
names = tf.concat(names, axis=0, name='names')
detected = tf.concat(detected, axis=0, name='detected')
arousal = tf.concat(arousal, axis=0, name='arousal')
valence = tf.concat(valence, axis=0, name='valence')
liking = tf.concat(liking, axis=0, name='liking')
istalkings = tf.concat(istalkings, axis=0, name='istalkings')
images = tf.concat(images, axis=0, name='images')
return names, detected, arousal, valence, liking, istalkings, images, iterator_train_all
我将有一个类似的开发方法;或者我可以将传递参数更改为该方法,以便我可以使用相同的方法两次。。。(不是问题)
然后:
请注意,必须在sess.run([names…])之前运行两个初始化sess.run(迭代器\u train\u all.initializer)
和sess.run(迭代器\u dev\u all.initializer)
,因为我想使用tf.cond
;将检索培训和验证示例,但tf.cond
将根据phase\u train
place\u holder只返回其中一个示例,这将确定我们是处于培训模式还是测试模式
证明:当我插入names=tf.Print(输入=[names],数据=[names],消息=[dev names')
在load\u devel\u sewa\tfrecords
下时;返回前;我得到:
dev names[\'Devel_01\' \'Devel_01\' \'Devel_02\'...]
在控制台中打印出来。即,在评估培训数据集时;tensorflow同时评估了devel数据集;但是tf.cond
输出了与训练数据集相关的tf记录
希望这个答案有帮助 也许你可以使用这个方法来完成这个特定的任务?例如,将训练集的循环长度设置为34,将块长度设置为2,应该足以循环浏览每条记录,然后从每条记录中生成2个示例?