TFDS now supports the Croissant 🥐 format! Read the documentation to know more.
tfds.features.Encoding
Stay organized with collections
Save and categorize content based on your preferences.
Encoding type of tfds.features.Tensor.
For higher dimension tensors, it is recommended to define the encoding as zlib or bytes to save space on disk.
Attributes | |
|---|---|
NONE
|
No compression (default). bools/integers will be upcasted to int64 as
this is the only integer format supported by the
tf.train.Example
protobufs in which examples are saved.
|
BYTES
|
Stored as raw bytes (avoid the upcasting from above). |
ZLIB
|
The raw bytes are compressed using zlib. |
Class Variables | |
|---|---|
| BYTES |
<Encoding.BYTES: 'bytes'>
|
| NONE |
<Encoding.NONE: 'none'>
|
| ZLIB |
<Encoding.ZLIB: 'zlib'>
|