python - 连体网络停留在 50% 的准确率

Question

我正在尝试构建一个连体网络来进行重新识别，该网络的最终输出应该是比较的特征向量，以确定输入图像是否来自同一类。我的模型的准确率停留在 50%。我尝试了损失函数、准确性和模型层的多种变化，但似乎没有任何效果，而且我在该领域的知识阻止了我尝试另一种方法。什么可能解决这个问题？

def cnn(in_dims):
    model = Sequential()
    model.add(Conv2D(8,(3,3),padding='same',input_shape=(in_dims[0],in_dims[1],in_dims[2]),activation='relu',name='conv1'))
    model.add(BatchNormalization())
    model.add(Activation('relu'))
    model.add(MaxPooling2D((2,2),(2,2),padding='same',name='pool1'))

    model.add(Conv2D(16,(3,3),padding='same',activation='relu',name='conv2'))
    model.add(BatchNormalization())
    model.add(Activation('relu'))
    model.add(MaxPooling2D((2,2),(2,2),padding='same',name='pool2'))

    model.add(Conv2D(32,(3,3),padding='same',activation='relu',name='conv3'))
    model.add(BatchNormalization())
    model.add(Activation('relu'))
    model.add(MaxPooling2D((2,2),(2,2),padding='same',name='pool3'))

    model.add(Conv2D(64,(3,3),padding='same',activation='relu',name='conv4'))
    model.add(BatchNormalization())
    model.add(Activation('relu'))
    model.add(MaxPooling2D((2,2),(2,2),padding='same',name='pool4'))

    model.add(Flatten(name='flatten'))
    model.add(Dense(64,name='embeddings'))

    return model

def double_loss(y_true, y_pred):
    total_length = y_pred.shape.as_list()[-1]

    image1 = y_pred[:,0:int(total_length*1/2)]
    image2 = y_pred[:,int(total_length*1/2):int(total_length*2/2)]

    dist = K.sum(K.square(image1 - image2), axis=1)

    return dist

def accuracy(y_true, y_pred):
    return K.mean(K.equal(y_true, K.cast(y_pred < 0.5, y_true.dtype)))

input_1 = Input(shape=(128,64,3,), name='input_1')
input_2 = Input(shape=(128,64,3,), name = 'input_2')

shared = cnn([128,64,3])

encoded_image1 = shared(input_1)
encoded_image2 = shared(input_2)

merged_vector = concatenate([encoded_image1, encoded_image2], axis=-1, name='merged_layer')

model = Model(inputs=[input_1, input_2], outputs=merged_vector)

model.compile(loss=double_loss, optimizer=Adam(lr = 0.0001, beta_1 = 0.9, beta_2 = 0.999), metrics=[accuracy])

history = model.fit([X_a_train, X_b_train], y=y_train,
                    batch_size=128, epochs=100, validation_data=[[X_a_val, X_b_val], y_val])

标签： pythontensorflowkerasneural-network