Quantizes then dequantizes a tensor.
tf.raw_ops.QuantizeAndDequantizeV3(
input,
input_min,
input_max,
num_bits,
signed_input=True,
range_given=True,
narrow_range=False,
axis=-1,
name=None
)
This is almost identical to QuantizeAndDequantizeV2, except that num_bits is a tensor, so its value can change during training.
Returns | |
---|---|
A Tensor . Has the same type as input .
|