TypeError:传递给参数“ input”的值的DataType int64不在允许值列表中:float16,bfloat16,float32,float64

时间:2019-11-08 15:49:49

标签: mnist tensorflow2.0 kaggle python-3.7.4

我正在尝试运行模型并根据mnist kaggle数据集预测测试数据。但是尝试进行预测时出现错误。原因和解决方法是什么?

    model = tf.keras.Sequential([
        tf.keras.layers.Conv2D(32, (3,3), padding='same', activation=tf.nn.relu,
                               input_shape=(28, 28, 1)),
        tf.keras.layers.MaxPooling2D((2, 2), strides=2),
        tf.keras.layers.Conv2D(64, (3,3), padding='same', activation=tf.nn.relu),
        tf.keras.layers.MaxPooling2D((2, 2), strides=2),
        tf.keras.layers.Flatten(input_shape=(28, 28, 1)),
        tf.keras.layers.Dense(128, activation=tf.nn.relu),
        tf.keras.layers.Dense(10,  activation=tf.nn.softmax)
    ])

test = pd.read_csv("test.csv") 
test.head()
CHANNELS = 1
IMAGE_SIZE = 28
IMAGE_WIDTH, IMAGE_HEIGHT = IMAGE_SIZE, IMAGE_SIZE
test = test.values.reshape(-1, IMAGE_WIDTH, IMAGE_HEIGHT, CHANNELS)
predictions = model.predict_classes(test, verbose=1)
  

TypeError:传递给参数'input'的值的DataType int64不在   允许值的列表:float16,bfloat16,float32,float64

1 个答案:

答案 0 :(得分:1)

正如TypeError所说,我认为step = 4 [l[i::step] for i in range(len(l)//(step-1))] # [[1, 5, 9], [2, 6, 10], [3, 7, 11], [4, 8, 12]] 数据帧包含test值,因此您必须像这样将类型更改为float:

int