我正在尝试构建一个分类器来对与其他人有光环效应的图像进行分类，我已经构建了一个keras模型：
model = Sequential()
model.add(Convolution2D(32, (3, 3),kernel_initializer=glorot_normal(), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(32, (3, 3),kernel_initializer=RandomNormal(stddev=0.01)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(64, (3, 3),kernel_initializer=RandomNormal(stddev=0.01)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(64,kernel_initializer=RandomNormal(stddev=0.01)))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(2,kernel_initializer=RandomNormal(stddev=0.01)))
model.add(Activation('sigmoid'))
sgd = optimizers.SGD(lr=0.001, decay=1e-6, momentum=0.09, nesterov=True)
model.compile( loss = "categorical_crossentropy",
optimizer = sgd,
metrics=['accuracy']
)
我甚至达到了95％的列车准确度，但验证准确率保持在65％，当我尝试使用模型预测图像时，它总是将其预测为一类所有被归类为具有光环的图像 .