keras运行debug解决protobuf版本冲突

# code 5.4 使用Keras实现异或网络
import numpy as np
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Activation
from tensorflow.keras.optimizers import SGD
x_train = np.array([
    [0, 0],
    [0, 1],
    [1, 0],
    [1, 1]
])
y_train = np.array([
    [0],
    [1],
    [1],
    [0]
])
model = Sequential()
num_neurons = 10
model.add(Dense(num_neurons, input_dim=2))
model.add(Activation('relu'))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.summary()

sgd = SGD(lr=0.1)
model.compile(loss='binary_crossentropy', optimizer=sgd, metrics=['accuracy'])
model.fit(x_train, y_train, epochs=100)
model.predict(x_train)

执行后报错:

_message.Message._CheckCalledFromGeneratedFile()
TypeError: Descriptors cannot not be created directly.
If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.
If you cannot immediately regenerate your protos, some other possible workarounds are:
 1. Downgrade the protobuf package to 3.20.x or lower.
 2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).

More information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates

Process finished with exit code 1

keras运行debug解决protobuf版本冲突_第1张图片

 解决方法:

 pip3 install --upgrade protobuf==3.20.1
keras运行debug解决protobuf版本冲突_第2张图片

提示安装的scipy的版本太高了,按照提示继续降级: pip3 install --upgrade scipy==1.4.1

keras运行debug解决protobuf版本冲突_第3张图片

再次运行代码

keras运行debug解决protobuf版本冲突_第4张图片

 完成 

你可能感兴趣的:(keras,tensorflow,protobuf)