Convert a TensorFlow GraphDef to TFLite. (deprecated)
tf.compat.v1.lite.toco_convert(
input_data, input_tensors, output_tensors, *args, **kwargs
)
This function is deprecated. Please use tf.lite.TFLiteConverter
API instead.
Conversion can be customized by providing arguments that are forwarded to
build_model_flags
and build_conversion_flags
(see documentation for
details).
Args:
input_data: Input data (i.e. often sess.graph_def
).
input_tensors: List of input tensors. Type and shape are computed using
foo.shape
and foo.dtype
.
output_tensors: List of output tensors (only .name is used from this).
*args: See build_model_flags
and build_conversion_flags
.
**kwargs: See build_model_flags
and build_conversion_flags
.
Returns | |
---|---|
The converted TensorFlow Lite model in a bytes array. |
Raises | |
---|---|
Defined in convert .
|