ResNet架构

from tensorflow.keras import Input, Modelfrom tensorflow.keras.layers import Conv2D, Concatenate, MaxPooling2Dfrom tensorflow.keras.utils import plot_modelRes_Input = Input(shape=(32,32,3))Res_Block_Con_Output01 = Conv2D(32, kernel_size=(3,3), activation='relu', padding='SAME')(Res_Input)Res_Block_Con_Output02 = Conv2D(32, kernel_size=(3,3), activation='relu', padding='SAME')(Res_Block_Con_Output01)Res_Block_Output = Concatenate()([Res_Input, Res_Block_Con_Output01, Res_Block_Con_Output02])Res_Model = Model(inputs=Res_Input, outputs=Res_Block_Output)

plot_model(Res_Model, dpi=300, show_shapes=True)

RNN(SimpleRNN)

import numpy as npData = np.array([[[0],[1]],[[1],[1]],[[1],[2]]])Target = np.array([1,2,0])

# One-hot encodingfrom tensorflow.keras.utils import to_categoricalX = to_categorical(Data)y = to_categorical(Target)

# 建构模型from tensorflow.keras.models import Sequentialfrom tensorflow.keras.layers import SimpleRNNRNN_Model = Sequential()RNN_Model.add(SimpleRNN(3, activation='softmax', input_shape=(2,3)))

# 训练模型RNN_Model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])RNN_Model.fit(X, y, epochs=500)