Creates a dataset that emits the records from one or more binary files.
tf.raw_ops.FixedLengthRecordDataset(
filenames,
header_bytes,
record_bytes,
footer_bytes,
buffer_size,
metadata='',
name=None
)
Args |
filenames
|
A Tensor of type string .
A scalar or a vector containing the name(s) of the file(s) to be
read.
|
header_bytes
|
A Tensor of type int64 .
A scalar representing the number of bytes to skip at the
beginning of a file.
|
record_bytes
|
A Tensor of type int64 .
A scalar representing the number of bytes in each record.
|
footer_bytes
|
A Tensor of type int64 .
A scalar representing the number of bytes to skip at the end
of a file.
|
buffer_size
|
A Tensor of type int64 .
A scalar representing the number of bytes to buffer. Must be > 0.
|
metadata
|
An optional string . Defaults to "" .
|
name
|
A name for the operation (optional).
|
Returns |
A Tensor of type variant .
|