将 tf model 转换为 TFlite model 时出错

Question

I am currently building a model to use it onto my nano 33 BLE sense board to predict weather by mesuring Humidity, Pressure, Temperature, I have 5 classes. I have used a kaggle dataset to train on it.

    df_labels = to_categorical(df.pop('Summary'))
    df_features = np.array(df)
    
    from sklearn.model_selection import train_test_split
    X_train, X_test, y_train, y_test = train_test_split(df_features, df_labels, test_size=0.15)
    
    normalize = preprocessing.Normalization()
    normalize.adapt(X_train)
    
    
    activ_func = 'gelu'
    model = tf.keras.Sequential([
                 normalize,
                 tf.keras.layers.Dense(units=6, input_shape=(3,)),
                 tf.keras.layers.Dense(units=100,activation=activ_func),
                 tf.keras.layers.Dense(units=100,activation=activ_func),
                 tf.keras.layers.Dense(units=100,activation=activ_func),
                 tf.keras.layers.Dense(units=100,activation=activ_func),
                 tf.keras.layers.Dense(units=5, activation='softmax')
    ])
    
    model.compile(optimizer='adam',#tf.keras.optimizers.Adagrad(lr=0.001),
                 loss='categorical_crossentropy',metrics=['acc'])
    model.summary()
    model.fit(x=X_train,y=y_train,verbose=1,epochs=15,batch_size=32, use_multiprocessing=True)

Then the model is trained, I want to convert it into a tflite model when I run the command convert I get the following message:

    # Convert the model to the TensorFlow Lite format without quantization
    converter = tf.lite.TFLiteConverter.from_keras_model(model)
    tflite_model = converter.convert()
    
    # Save the model to disk
    open("gesture_model.tflite", "wb").write(tflite_model)
      
    import os
    basic_model_size = os.path.getsize("gesture_model.tflite")
    print("Model is %d bytes" % basic_model_size)




    <unknown>:0: error: failed while converting: 'main': Ops that can be supported by the flex runtime (enabled via setting the -emit-select-tf-ops flag):
        tf.Erf {device = ""}

For your information I use google colab to design the model.

If anyone has any idea or solution to this issue, I would be glad to hear it !

Answer 1

This often happens when you have not set the converter's supported Operations.

Here is an example:

import tensorflow as tf

converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)

converter.target_spec.supported_ops = [
  tf.lite.OpsSet.TFLITE_BUILTINS, # enable TensorFlow Lite ops.
  tf.lite.OpsSet.SELECT_TF_OPS # enable TensorFlow ops.
]

tflite_model = converter.convert()
open("converted_model.tflite", "wb").write(tflite_model)

This list of supported operations are constantly changing so in case the error still appears you can also try to set the experimental converter features as follow:

converter.experimental_new_converter = True

Answer 2

I solved the problem. It was the activation function 'gelu' not yet supported by TFlite. I changed it to 'relu' and no more problem.