BentoML

for a tensorflow model to work, users have to explicitly define the signature of the model with the decorator `@tf.function` . Usually, inference function that is used by default by tensorflow is `__call__` : (an toy example)

```class NativeModel(tf.Module):
    def __init__(self):
        super().__init__()
        self.weights = np.asfarray([[1.0], [1.0], [1.0], [1.0], [1.0]])
        self.dense = lambda inputs: tf.matmul(inputs, self.weights)

    @tf.function(
        input_signature=[tf.TensorSpec(shape=[1, 5], dtype=tf.float64, name="inputs")]
    )
    def __call__(self, inputs):
        return self.dense(inputs)```

I believe that this <https://www.tensorflow.org/guide/function> from Tensorflow goes into how the decorator works. a lot more thoroughly. Let me know if you still need any help