我是TensorFlow和机器学习的新手。我正在尝试创建自己的文本分类。我遇到了下面的问题。在Android上加载tflite模型时，出现了下面的错误。
Process: org.tensorflow.lite.examples.textclassification, PID: 12031java.lang.IllegalStateException: 内部错误: 准备张量分配时出现意外失败: 遇到未解析的自定义操作: TensorListFromTensor。节点编号4(TensorListFromTensor)准备失败。 at org.tensorflow.lite.NativeInterpreterWrapper.allocateTensors(Native Method) at org.tensorflow.lite.NativeInterpreterWrapper.init(NativeInterpreterWrapper.java:96) at org.tensorflow.lite.NativeInterpreterWrapper.<init>(NativeInterpreterWrapper.java:61) at org.tensorflow.lite.Interpreter.<init>(Interpreter.java:224) at org.tensorflow.lite.Interpreter.<init>(Interpreter.java:182) at org.tensorflow.lite.examples.textclassification.TextClassificationClient.loadModel(TextClassificationClient.java:139) at org.tensorflow.lite.examples.textclassification.TextClassificationClient.load(TextClassificationClient.java:129) at org.tensorflow.lite.examples.textclassification.MainActivity.lambda$onStart$1$MainActivity(MainActivity.java:65) at org.tensorflow.lite.examples.textclassification.-$$Lambda$MainActivity$3O7XdyFVukGQ46LZyOIpHdTRepg.run(Unknown Source:2) at android.os.Handler.handleCallback(Handler.java:873) at android.os.Handler.dispatchMessage(Handler.java:99) at android.os.Looper.loop(Looper.java:193) at android.app.ActivityThread.main(ActivityThread.java:6898) at java.lang.reflect.Method.invoke(Native Method) at com.android.internal.os.RuntimeInit$MethodAndArgsCaller.run(RuntimeInit.java:537) at com.android.internal.os.ZygoteInit.main(ZygoteInit.java:858)Py Notebook代码
input = tf.keras.layers.Input(shape=(max_len,))x = tf.keras.layers.Embedding(max_words, embed_size, weights=[embedding_matrix], trainable=False)(input)x = tf.keras.layers.Bidirectional(tf.keras.layers.GRU(128, return_sequences=True, dropout=0.1, recurrent_dropout=0.1))(x)x = tf.keras.layers.Conv1D(64, kernel_size=3, padding="valid", kernel_initializer="glorot_uniform")(x)avg_pool = tf.keras.layers.GlobalAveragePooling1D()(x)max_pool = tf.keras.layers.GlobalMaxPooling1D()(x)x = tf.keras.layers.concatenate([avg_pool, max_pool])preds = tf.keras.layers.Dense(6, activation="sigmoid")(x)model = tf.keras.Model(input, preds)model.summary()在Python中运行下面的代码也会导致同样的错误
interpreter = tf.lite.Interpreter(model_path="xxx.tflite")interpreter.allocate_tensors()下面的错误---------------------------------------------------------------------------RuntimeError Traceback (most recent call last)<ipython-input-20-988ba8e1e2e5> in <module> 1 interpreter = tf.lite.Interpreter(model_path="touch_tf.tflite")----> 2 interpreter.allocate_tensors()/usr/local/lib/python3.7/site-packages/tensorflow_core/lite/python/interpreter.py in allocate_tensors(self) 240 def allocate_tensors(self): 241 self._ensure_safe()--> 242 return self._interpreter.AllocateTensors() 243 244 def _safe_to_run(self):/usr/local/lib/python3.7/site-packages/tensorflow_core/lite/python/interpreter_wrapper/tensorflow_wrap_interpreter_wrapper.py in AllocateTensors(self) 108 109 def AllocateTensors(self):--> 110 return _tensorflow_wrap_interpreter_wrapper.InterpreterWrapper_AllocateTensors(self) 111 112 def Invoke(self):RuntimeError: 遇到未解析的自定义操作: TensorListFromTensor。节点编号4(TensorListFromTensor)准备失败。回答：
这个链接帮助我解决了这个问题。
设置converter.experimental_new_converter =True会有所帮助
