machine-learning - 检索输入 0 与层 model_6 错误不兼容

Question

我正在尝试使用 cifar10 数据集在代码下方运行，但代码中出现错误。

(X_train, y_train), (X_test, y_test) = cifar10.load_data()
X_train = X_train.astype('float32') 
X_test = X_test.astype('float32') 
X_train = X_train / 255.0 
X_test = X_test / 255.0
y_train = tf.keras.utils.to_categorical(y_train) 
y_test = tf.keras.utils.to_categorical(y_test) 
num_classes = y_test.shape[1]
test_img =image.load_img('test.jpg',target_size =(32,32))
test_img =image.img_to_array(test_img) 
image =np.expand_dims(test_img, axis =0) 
def iterate_mode(model, input_image):
    data_input = input_image
    for layer in model.layers:
        input=Input(shape=model.get_layer( layer.name ).get_input_shape_at( 0 ))
        out = layer( input )
        new_model = keras.models.Model(inputs=input, outputs=out )
        out = new_model.predict(data_input)
        data_input = out
   
 result = iterate_model(model,image)

请找出以下错误

/usr/local/lib/python3.7/dist-packages/keras/engine/base_layer.py:989 __call__  *
    input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
/usr/local/lib/python3.7/dist-packages/keras/engine/input_spec.py:264 assert_input_compatibility  *
    raise ValueError('Input ' + str(input_index) +

ValueError: Input 0 is incompatible with layer model_6: expected shape=(None, None, 32, 32, 3), found shape=(None, 32, 32, 3)

标签： machine-learningkerasconv-neural-network