（1）下载MNIST数据集； （2）采用深度学习网络，训练手写数字识别模型； 编写GUI界面，输入测试数字图片，调用识别模型，输出识别结果。代码

好的，以下是实现手写数字识别的Python代码：

# 导入必要的库
import tensorflow as tf
from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D
from tensorflow.keras.utils import to_categorical
import numpy as np
import matplotlib.pyplot as plt
from tkinter import *
from tkinter import filedialog
from PIL import ImageTk, Image

# 下载MNIST数据集
(x_train, y_train), (x_test, y_test) = mnist.load_data()

# 数据预处理
x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)
x_test = x_test.reshape(x_test.shape[0], 28, 28, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
y_train = to_categorical(y_train, 10)
y_test = to_categorical(y_test, 10)

# 构建深度学习网络
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(28, 28, 1)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))

# 编译模型
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

# 训练模型
model.fit(x_train, y_train, epochs=10, batch_size=32, verbose=1, validation_data=(x_test, y_test))

# 创建GUI界面
root = Tk()
root.title('手写数字识别')
root.geometry('400x400')

# 加载图像
def load_img():
    path = filedialog.askopenfilename()
    img = Image.open(path).resize((28, 28))
    img = ImageTk.PhotoImage(img)
    label_img.config(image=img)
    label_img.image = img
    predict_img(img)

# 预测图像
def predict_img(img):
    img_arr = np.array(img)
    img_arr = img_arr[:, :, :1]
    img_arr = img_arr.astype('float32') / 255
    pred = model.predict(np.array([img_arr]))
    result = np.argmax(pred)
    label_result.config(text='识别结果：{}'.format(result))

# 显示图像
label_img = Label(root)
label_img.pack()

# 加载图像按钮
btn_load = Button(root, text='加载图像', command=load_img)
btn_load.pack()

# 识别结果标签
label_result = Label(root, text='识别结果：')
label_result.pack()

# 运行界面
root.mainloop()

这个代码中，首先下载MNIST数据集并进行数据预处理，然后构建一个卷积神经网络，训练模型，并用Tkinter创建一个GUI界面。当用户点击“加载图像”按钮时，程序调用预测函数对图像进行预测，并将结果显示在GUI界面上。希望这个代码对你有帮助！