如何将签名密钥添加到 keras 模型

Posted 2023-02-16

【中文标题】如何将签名密钥添加到 keras 模型

【英文标题】：How to add signature key to a keras model

【发布时间】：2022-01-16 00:35:12

【问题描述】：

我正在构建一个 tensorflow keras 模型，该模型必须转换为 tensorflowlite 并在 Kotlin 中运行。该模型在 Anaconda Spyder 中运行良好。但是当我尝试将此模型转换为 tensorflow lite 时，我遇到了错误。

class OneStep(tf.keras.Model):
  def __init__(self, model, chars_from_ids, ids_from_chars, temperature=1.0):
    super().__init__()
    self.temperature = temperature
    self.model = model
    self.chars_from_ids = chars_from_ids
    self.ids_from_chars = ids_from_chars

    # Create a mask to prevent "[UNK]" from being generated.
    skip_ids = self.ids_from_chars(['[UNK]'])[:, None]
    sparse_mask = tf.SparseTensor(
        # Put a -inf at each bad index.
        values=[-float('inf')]*len(skip_ids),
        indices=skip_ids,
        # Match the shape to the vocabulary
        dense_shape=[len(ids_from_chars.get_vocabulary())])
    self.prediction_mask = tf.sparse.to_dense(sparse_mask)

  @tf.function
  def generate_one_step(self, inputs, states=None):
    # Convert strings to token IDs.
    input_chars = tf.strings.unicode_split(inputs, 'UTF-8')
    input_ids = self.ids_from_chars(input_chars).to_tensor()

    # Run the model.
    # predicted_logits.shape is [batch, char, next_char_logits]
    predicted_logits, states = self.model(inputs=input_ids, states=states,
                                          return_state=True)
    # Only use the last prediction.
    predicted_logits = predicted_logits[:, -1, :]
    predicted_logits = predicted_logits/self.temperature
    # Apply the prediction mask: prevent "[UNK]" from being generated.
    predicted_logits = predicted_logits + self.prediction_mask

    # Sample the output logits to generate token IDs.
    predicted_ids = tf.random.categorical(predicted_logits, num_samples=1)
    predicted_ids = tf.squeeze(predicted_ids, axis=-1)

    # Convert from token ids to characters
    predicted_chars = self.chars_from_ids(predicted_ids)

    # Return the characters and model state.
    return predicted_chars, states

one_step_model = OneStep(model, chars_from_ids, ids_from_chars)

tf.saved_model.save(one_step_model, 'one_step')

我尝试在这段代码摘录中将此模型转换为 tensorflowlite。我试图在 Anaconda Spyder 中转换模型，但它至少需要一个签名密钥。我不确定如何使用签名密钥首先保存模型。

one_step_reloaded = tf.saved_model.load('one_step')
#print(one_step_reloaded.SignatureDefEntry)

# Convert the model
converter = tf.lite.TFLiteConverter.from_saved_model('one_step') # path to the SavedModel directory
tflite_model = converter.convert()

# Save the model.
with open('Bible.tflite', 'wb') as f:
  f.write(tflite_model)


 raise ValueError("Only support at least one signature key.")

ValueError: Only support at least one signature key.

您能帮忙在保存之前如何将签名密钥添加到此模型，以便可以将其转换为 tensorflowlite 吗？

【参考方案1】：

由于您使用的是 Keras 模型，因此您可以使用 TFLiteConverter.from_keras_model API 直接从该格式转换为 TensorFlow Lite。举个例子：

# Convert the model.
converter = tf.lite.TFLiteConverter.from_keras_model(model)
tflite_model = converter.convert()

# Save the model.
with open('model.tflite', 'wb') as f:
  f.write(tflite_model)

【讨论】：

我现在收到一个新错误。如果不是 isinstance(self._keras_model.call, _def_function.Function): AttributeError: '_UserObject' 对象没有属性 'call'