【发布时间】:2019-04-20 23:44:15
【问题描述】:
我坚持让 tfrecords 为图像-文本对数据工作。
这是从图像特征的 numpy 数组和文本文件创建 tfrecord 的代码,
def npy_to_tfrecords(numpy_array, text_file, output_file):
f = open(text_file)
# write records to a tfrecords file
writer = tf.python_io.TFRecordWriter(output_file)
# Loop through all the features you want to write
for X, line in zip(numpy_array, f) :
#let say X is of np.array([[...][...]])
#let say y is of np.array[[0/1]]
txt = "{}".format(line[:-1])
txt = txt.encode()
# Feature contains a map of string to feature proto objects
feature = {}
feature['x'] = tf.train.Feature(float_list=tf.train.FloatList(value=X.flatten()))
feature['y'] = tf.train.Feature(bytes_list=tf.train.BytesList(value=[txt]))
# Construct the Example proto object
example = tf.train.Example(features=tf.train.Features(feature=feature))
# Serialize the example to a string
serialized = example.SerializeToString()
# write the serialized objec to the disk
writer.write(serialized)
writer.close()
在此之后我无法制作数据集:
def load_data_tfr():
train = tf.data.TFRecordDataset("train.tfrecord")
# example proto decode
def _parse_function1(example_proto):
keys_to_features = {'x': tf.FixedLenFeature(2048, tf.float32),
'y': tf.VarLenFeature(tf.string) }
parsed_features = tf.parse_single_example(example_proto, keys_to_features)
return {"x": parsed_features['x'], "y": parsed_features['y']} # ['x'], parsed_features['y']
# Parse the record into tensors.
train = train.map(_parse_function1)
return train
我保留 .得到错误:
train_data = load_data_tfr()
random.shuffle(train_data)
for i in reversed(range(1, len(x))): TypeError: object of type 'MapDataset' has no len()
有什么帮助吗?谢谢。
【问题讨论】:
标签: python tensorflow tensorflow-datasets tfrecord