将序列模型中Keras中的两个损失函数与ndarray输出组合

2024-05-05 • 问答

我正在用Keras训练cnn模型（图像和LiDAR中的物体检测（Kaggle Lyft Competition）。作为输出，我有一个34通道围带。因此，输出尺寸为：LENGTH x WIDTH X 34。前10个通道用于不同类别的对象（最好是一个热矢量），其余24个通道是3D边界框的坐标。

对于前10个频道，我想使用：keras.losses.categorical_crossentropy，对于其余24个频道：keras.losses.mean_squared_error

此外，由于对象的数量差异很大，为避免偏差，我在对每个类进行权衡。由于输出是ndarray，因此我不得不编写自定义损失函数（用于类加权）。代码主要来自： Custom loss function for U-net in keras using class weights: `class_weight` not supported for 3+ dimensional targets

def weightedLoss(weightsList):

def lossFunc(true,pred):

    axis = -1 #if channels last 
    #axis=  1 #if channels first


    #argmax returns the index of the element with the greatest value
    #done in the class axis,it returns the class index    
    classSelectors = K.argmax(true,axis=axis) 

    #considering weights are ordered by class,for each class
    #true(1) if the class index is equal to the weight index   
    one64 = np.ones(1,dtype=np.int64)  #Needed to avod int32 and int64 error
    classSelectors = [K.equal(one64[0]*i,classSelectors) for i in range(len(weightsList))]

    #casting boolean to float for calculations  
    #each tensor in the list contains 1 where ground true class is equal to its index 
    #if you sum all these,you will get a tensor full of ones. 
    classSelectors = [K.cast(x,K.floatx()) for x in classSelectors]

    #for each of the selections above,multiply their respective weight
    weights = [sel * w for sel,w in zip(classSelectors,weightsList)] 

    #sums all the selections
    #result is a tensor with the respective weight for each element in predictions
    weightMultiplier = weights[0]
    for i in range(1,len(weights)):
        weightMultiplier = weightMultiplier + weights[i]

    op_chan_loss = keras.losses.categorical_crossentropy
    op_box_loss = keras.losses.mean_squared_error
    #make sure your originalLossFunc only collapses the class axis
    #you need the other axes intact to multiply the weights tensor
    print(type(true),type(pred))
    loss = op_chan_loss(true,pred) 
    loss = loss * weightMultiplier

    return loss
return lossFunc

但是，我不确定如何在此自定义损失函数中将两个损失函数组合在一起。请帮忙。

使用两个输出。您的模型必须是Functional API模型：

#basic example of the initial part of your model
inputs = Input(input_shape)
intermediate_output = Conv2D(...)(inputs)
intermediate_output = Conv2D(...)(intermediate_output)

在模型中的某个点，您将分离两个分支。也许最后一层或更早（由于两个输出的性质不同，也许（需要测试），每个输出都需要一层或两层才能更好地适应。

output1 = SomeLayer(...)(intermediate_output)
....
output1 = Dense(10,activation='softmax',name='cat_out')(output1) 


output2 = SomeLayer(...)(intermediate_output)
....
output2 = SomeLayer(24,name='bound_out')(output2) #maybe choose an activation

创建具有两个输出的模型：

model = Model(inputs,[output1,output2])

现在，您可以为每个输出使用不同的损失函数，并使用不同的指标：

model.compile(loss = [weightedLoss(weights),'mse'],metrics = {'cat_out':[metrics1],'bound_out':[metrics2],optimizer = ...)

训练有两个输出：

model.fit(x_train,[y_train[:,:,:10],y_train[:,-24:]],...)

我没有检查您的损失函数，但我看到它有循环（通常对张量运算不利）。

我建议您的体重清单为张量：

weightsTensor = K.constant(listOfWeights)

在选择权重时，请尝试使用tf.gather或tf.gather_nd。我没有花时间思考什么是正确的函数以及如何使用它，但是一旦完成，您只需将结果乘以权重即可：

#this may need change and might be a little troublesome to understand
selectedWeights = tf.gather_nd(weightsTensor,classSelectors,....) 

loss = keras.losses.categorical_crossentropy(true,pred)
loss = selectedWeights * loss

将序列模型中Keras中的两个损失函数与ndarray输出组合

zhang4xue1 回答：将序列模型中Keras中的两个损失函数与ndarray输出组合

大家都在问