想写一下手写数字识别体，但是没出来图片

问题遇到的现象和发生背景

，想问一下大家怎么弄一下呀

问题相关代码，请勿粘贴截图

from configparser import ConfigParser
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt


mnist=tf.keras.datasets.mnist
(train_x,train_y),(test_x,test_y)=mnist.load_data()

x_train=tf.cast(train_x/255.0,tf.float32)
x_test=tf.cast(test_x/255.0,tf.float32)
y_train=tf.cast(train_y,tf.int16)
y_test=tf.cast(test_y,tf.int16)

model=tf.keras.Sequential( [ tf.keras.layers.Flatten(input_shape=(28,28)), 
                             tf.keras .layers.Dense(128,activation='relu'),
                            tf.keras.layers.Dense(10,activation='softmax') ]  )
model.summary()

model.compile(optimize='adam',loss=tf.keras.losses.SparseCategoricalCrossentropy(),metrics=['sparse_categorical_accuracy'])
history=model.fit(x_train,batch_size=32,epochs=5,validation_split=0.2)

loss,acc=model.evaluate(x_test,y_test,verbose=2)
result=model.predict([[x_test[111]]])

print(result)
print('模型识别的结果是：',np.argmax(model.predict([[test_x[123]]])))

plt.imshow(test_x[123],camp='gray')
plt.show()

运行结果及报错内容

TypeError: Invalid keyword argument(s) in compile(): ({'optimize'},). Valid keyword arguments include "cloning", "experimental_run_tf_function", "distribute", "target_tensors", or "sample_weight_mode".

我的解答思路和尝试过的方法

我想要达到的结果

能运行出数字图片