# 简单的TensorFlow示例
import tensorflow as tf

# 创建一个简单的神经网络
model = tf.keras.Sequential([
tf.keras.layers.Dense(64, activation=’relu’, input_shape=(784,)),
tf.keras.layers.Dense(10, activation=’softmax’)
])

# 编译模型
model.compile(optimizer=’adam’,
loss=’sparse_categorical_crossentropy’,
metrics=[‘accuracy’])

# 打印模型摘要
model.summary()
Model: “sequential”
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense (Dense) (None, 64) 50240
dense_1 (Dense) (None, 10) 650
=================================================================
Total params: 50,890
Trainable params: 50,890
Non-trainable params: 0
_________________________________________________________________

# 简单的PyTorch示例
import torch
import torch.nn as nn
import torch.optim as optim

# 创建一个简单的神经网络
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.fc1 = nn.Linear(784, 64)
self.fc2 = nn.Linear(64, 10)

def forward(self, x):
x = torch.relu(self.fc1(x))
x = torch.softmax(self.fc2(x), dim=1)
return x

# 实例化模型
model = Net()

# 打印模型
print(model)
Net(
(fc1): Linear(in_features=784, out_features=64, bias=True)
(fc2): Linear(in_features=64, out_features=10, bias=True)
)

# 简单的Keras示例
from keras.models import Sequential
from keras.layers import Dense

# 创建一个简单的神经网络
model = Sequential()
model.add(Dense(64, activation=’relu’, input_dim=784))
model.add(Dense(10, activation=’softmax’))

# 编译模型
model.compile(optimizer=’adam’,
loss=’sparse_categorical_crossentropy’,
metrics=[‘accuracy’])

# 打印模型摘要
model.summary()
Model: “sequential”
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense (Dense) (None, 64) 50240
dense_1 (Dense) (None, 10) 650
=================================================================
Total params: 50,890
Trainable params: 50,890
Non-trainable params: 0
_________________________________________________________________

app = Flask(__name__)

# 加载模型
model = tf.keras.models.load_model(‘model.h5’)

@app.route(‘/predict’, methods=[‘POST’])
def predict():
# 获取输入数据
data = request.get_json()
# 进行预测
prediction = model.predict([data[‘input’]])
# 返回预测结果
return jsonify({‘prediction’: prediction.tolist()})

if __name__ == ‘__main__’:
app.run(host=’0.0.0.0′, port=5000)

# 启动服务
# python app.py
# * Running on http://0.0.0.0:5000/ (Press CTRL+C to quit)

# 模拟模型性能数据
time = np.arange(0, 30, 1)
accuracy = np.random.normal(0.95, 0.02, 30)
l latency = np.random.normal(0.1, 0.01, 30)

# 绘制性能图表
plt.figure(figsize=(12, 6))
plt.subplot(2, 1, 1)
plt.plot(time, accuracy)
plt.title(‘模型准确率’)
plt.xlabel(‘时间（天）’)
plt.ylabel(‘准确率’)

plt.subplot(2, 1, 2)
plt.plot(time, latency)
plt.title(‘模型延迟’)
plt.xlabel(‘时间（天）’)
plt.ylabel(‘延迟（秒）’)

plt.tight_layout()
plt.show()