How to use Dataset API to read TFRecords file of lists of variant length?

问题

I want to use Tensorflow's Dataset API to read TFRecords file of lists of variant length. Here is my code.

def _int64_feature(value):
    # value must be a numpy array.
    return tf.train.Feature(int64_list=tf.train.Int64List(value=value))
def main1():
    # Write an array to TFrecord.
    # a is an array which contains lists of variant length.
    a = np.array([[0, 54, 91, 153, 177],
                 [0, 50, 89, 147, 196],
                 [0, 38, 79, 157],
                 [0, 49, 89, 147, 177],
                 [0, 32, 73, 145]])

    writer = tf.python_io.TFRecordWriter('file')

    for i in range(a.shape[0]): # i = 0 ~ 4
        x_train = a[i]
        feature = {'i': _int64_feature(np.array([i])), 'data': _int64_feature(x_train)}

        # Create an example protocol buffer
        example = tf.train.Example(features=tf.train.Features(feature=feature))

        # Serialize to string and write on the file
        writer.write(example.SerializeToString())

    writer.close()

    # Check TFRocord file.
    record_iterator = tf.python_io.tf_record_iterator(path='file')
    for string_record in record_iterator:
        example = tf.train.Example()
        example.ParseFromString(string_record)

        i = (example.features.feature['i'].int64_list.value)
        data = (example.features.feature['data'].int64_list.value)
        #data = np.fromstring(data_string, dtype=np.int64)
        print(i, data)

    # Use Dataset API to read the TFRecord file.
    def _parse_function(example_proto):
        keys_to_features = {'i'   :tf.FixedLenFeature([], tf.int64),
                            'data':tf.FixedLenFeature([], tf.int64)}
        parsed_features = tf.parse_single_example(example_proto, keys_to_features)
        return parsed_features['i'], parsed_features['data']

    ds = tf.data.TFRecordDataset('file')
    iterator = ds.map(_parse_function).make_one_shot_iterator()
    i, data = iterator.get_next()
    with tf.Session() as sess:
        print(i.eval())
        print(data.eval())

Check TFRecord file

[0] [0, 54, 91, 153, 177]
[1] [0, 50, 89, 147, 196]
[2] [0, 38, 79, 157]
[3] [0, 49, 89, 147, 177]
[4] [0, 32, 73, 145]

But it showed the following error when I tried to use Dataset API to read TFRecord file.

tensorflow.python.framework.errors_impl.InvalidArgumentError: Name: , Key: data, Index: 0. Number of int64 values != expected. Values size: 5 but output shape: []

Thank you.
UPDATE: I tried to use the following code to read TFRecord with Dataset API, but both of them failed.

def _parse_function(example_proto):
    keys_to_features = {'i'   :tf.FixedLenFeature([], tf.int64),
                        'data':tf.VarLenFeature(tf.int64)}
    parsed_features = tf.parse_single_example(example_proto, keys_to_features)
    return parsed_features['i'], parsed_features['data']

ds = tf.data.TFRecordDataset('file')
iterator = ds.map(_parse_function).make_one_shot_iterator()
i, data = iterator.get_next()
with tf.Session() as sess:
    print(sess.run([i, data]))

def _parse_function(example_proto):
    keys_to_features = {'i'   :tf.VarLenFeature(tf.int64),
                        'data':tf.VarLenFeature(tf.int64)}
    parsed_features = tf.parse_single_example(example_proto, keys_to_features)
    return parsed_features['i'], parsed_features['data']

ds = tf.data.TFRecordDataset('file')
iterator = ds.map(_parse_function).make_one_shot_iterator()
i, data = iterator.get_next()
with tf.Session() as sess:
    print(sess.run([i, data]))

And the error:

Traceback (most recent call last): File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/tensor_util.py", line 468, in make_tensor_proto str_values = [compat.as_bytes(x) for x in proto_values] File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/tensor_util.py", line 468, in str_values = [compat.as_bytes(x) for x in proto_values] File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/util/compat.py", line 65, in as_bytes (bytes_or_text,)) TypeError: Expected binary or unicode string, got

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "2tfrecord.py", line 126, in main1() File "2tfrecord.py", line 72, in main1 iterator = ds.map(_parse_function).make_one_shot_iterator() File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/data/ops/dataset_ops.py", line 712, in map return MapDataset(self, map_func) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/data/ops/dataset_ops.py", line 1385, in init self._map_func.add_to_graph(ops.get_default_graph()) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/function.py", line 486, in add_to_graph self._create_definition_if_needed() File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/function.py", line 321, in _create_definition_if_needed self._create_definition_if_needed_impl() File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/function.py", line 338, in _create_definition_if_needed_impl outputs = self._func(*inputs) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/data/ops/dataset_ops.py", line 1376, in tf_map_func flattened_ret = [ops.convert_to_tensor(t) for t in nest.flatten(ret)] File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/data/ops/dataset_ops.py", line 1376, in flattened_ret = [ops.convert_to_tensor(t) for t in nest.flatten(ret)] File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 836, in convert_to_tensor as_ref=False) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 926, in internal_convert_to_tensor ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/constant_op.py", line 229, in _constant_tensor_conversion_function return constant(v, dtype=dtype, name=name) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/constant_op.py", line 208, in constant value, dtype=dtype, shape=shape, verify_shape=verify_shape)) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/tensor_util.py", line 472, in make_tensor_proto "supported type." % (type(values), values)) TypeError: Failed to convert object of type to Tensor. Contents: SparseTensor(indices=Tensor("ParseSingleExample/Slice_Indices_i:0", shape=(?, 1), dtype=int64), values=Tensor("ParseSingleExample/ParseExample/ParseExample:3", shape=(?,), dtype=int64), dense_shape=Tensor("ParseSingleExample/Squeeze_Shape_i:0", shape=(1,), dtype=int64)). Consider casting elements to a supported type.

Python version: 3.5.2
Tensorflow version: 1.4.1

回答1:

After hours of searching and trying, I believe the answer emerges. Below is my code.

def _int64_feature(value):
    # value must be a numpy array.
    return tf.train.Feature(int64_list=tf.train.Int64List(value=value.flatten()))

# Write an array to TFrecord.
# a is an array which contains lists of variant length.
a = np.array([[0, 54, 91, 153, 177],
              [0, 50, 89, 147, 196],
              [0, 38, 79, 157],
              [0, 49, 89, 147, 177],
              [0, 32, 73, 145]])

writer = tf.python_io.TFRecordWriter('file')

for i in range(a.shape[0]): # i = 0 ~ 4
    x_train = np.array(a[i])
    feature = {'i'   : _int64_feature(np.array([i])), 
               'data': _int64_feature(x_train)}

    # Create an example protocol buffer
    example = tf.train.Example(features=tf.train.Features(feature=feature))

    # Serialize to string and write on the file
    writer.write(example.SerializeToString())

writer.close()

# Check TFRocord file.
record_iterator = tf.python_io.tf_record_iterator(path='file')
for string_record in record_iterator:
    example = tf.train.Example()
    example.ParseFromString(string_record)

    i = (example.features.feature['i'].int64_list.value)
    data = (example.features.feature['data'].int64_list.value)
    print(i, data)

# Use Dataset API to read the TFRecord file.
filenames = ["file"]
dataset = tf.data.TFRecordDataset(filenames)
def _parse_function(example_proto):
    keys_to_features = {'i':tf.VarLenFeature(tf.int64),
                        'data':tf.VarLenFeature(tf.int64)}
    parsed_features = tf.parse_single_example(example_proto, keys_to_features)
    return tf.sparse_tensor_to_dense(parsed_features['i']), \
           tf.sparse_tensor_to_dense(parsed_features['data'])
# Parse the record into tensors.
dataset = dataset.map(_parse_function)
# Shuffle the dataset
dataset = dataset.shuffle(buffer_size=1)
# Repeat the input indefinitly
dataset = dataset.repeat()  
# Generate batches
dataset = dataset.batch(1)
# Create a one-shot iterator
iterator = dataset.make_one_shot_iterator()
i, data = iterator.get_next()
with tf.Session() as sess:
    print(sess.run([i, data]))
    print(sess.run([i, data]))
    print(sess.run([i, data]))

There are few things to note.
1. This SO question helps a lot.
2. tf.VarLenFeature would return SparseTensor, thus, using tf.sparse_tensor_to_dense to convert to dense tensor is necessary.
3. In my code, parse_single_example() can't be replaced with parse_example(), and it bugs me for a day. I don't know why parse_example() doesn't work out. If anyone know the reason, please enlighten me.

回答2:

The error is very simple. Your data is not FixedLenFeature it is VarLenFeature. Replace your line:

 'data':tf.FixedLenFeature([], tf.int64)}

with

 'data':tf.VarLenFeature(tf.int64)}

Also, when you call print(i.eval()) and print(data.eval()) you are calling the iterator twice. The first print will print 0, but the second one will print the value of the second row [ 0, 50, 89, 147, 196]. You can do print(sess.run([i, data])) to get i and data from the same row.

来源：https://stackoverflow.com/questions/47939537/how-to-use-dataset-api-to-read-tfrecords-file-of-lists-of-variant-length

标签

python

tensorflow

tfrecord