3 Replies
      Latest reply on Sep 24, 2019 1:46 AM by kerfuffle
      shazsaleem10 Level 1 Level 1 (0 points)

        I have tried various ways to convert my Keras model to core ml using core ml tools, but it gives me this error.

        Keras layer '<class 'tensorflow.python.keras.engine.input_layer.InputLayer'>' not supported.

         

         

        This is how my model looks.



        img_input = layers.Input(shape=(224, 224, 3))

         

        seed = 230

        numpy.random.seed(seed)

         

         

        x = layers.Conv2D(16, 3, activation='relu')(img_input)

        x = layers.MaxPooling2D(2)(x)

        x = layers.Conv2D(32, 3, activation='relu')(x)

        x = layers.MaxPooling2D(2)(x)

        x = layers.Flatten()(x)

        x = layers.Dense(128, activation='relu')(x)

        x = layers.Dropout(0.4)(x)

         

        output = layers.Dense(3, activation='softmax')(x)

         

         

        model = Model(img_input, output)

        model.compile(loss='sparse_categorical_crossentropy', optimizer='adam', metrics=['accuracy'])