正确的损失函数方式 [英] Correct way of loss function

问题描述

我一直在尝试在keras中实现损失功能.但是我无法找到一种方法来传递除loss(y_true，y_predict)以外的2个以上参数，因此我想到了使用lambda层作为最后一层，并在lambda层itslef中进行计算，并简单地返回y_predict的值像这样的损失功能

Hi I have been trying to implement a loss function in keras. But i was not able to figure a way to pass more than 2 arguments other than loss(y_true, y_predict) so I thought of using a lambda layer as the last layer and doing my computation in lambda layer itslef and simply returning the value of y_predict in loss function like this

def loss_function(x):
    loss = some calculations
    return loss

def dummy_loss(y_true, y_pred):
    return y_pred

def primary_network():
    global prim_binary_tensor
    x = VGG16(weights='imagenet', include_top=True, input_shape=image_shape)
    last_layer = Dense(k_bit, activation='tanh', name='Dense11')(x.layers[-1].output)
    last_layer, x = basic_model()
    lambda_layer = Lambda(loss_function)([last_layer, prim_binary_tensor])
    model = Model(inputs=[x.input, prim_binary_tensor], outputs=[lambda_layer])
    model.compile(optimizer="adam", loss=dummy_loss,metrics=['accuracy'])
    return model

所以我的问题是:

1)我是用正确的方法来计算损失吗?是否保证为每个图像(input_data)调用lambda图层函数?

1) Am I doing it the right way to calculate the loss? Is it guranteed that the lambda layer function is called for each and every image(input_data)?

2)有人可以建议我如何将多个参数传递给损失函数吗?

2) Can someone suggest me how to pass multiple arguments to a loss function?

3)损失函数的最终结果可以是标量还是必须是向量或矩阵?

3) Can the final outcome of a loss function be a scalar or it has to be a vector or matrix?

推荐答案

回答您的问题:

1. 我不知道您的方法是否可行，但是有一个更简单的解决方案.

1. I don't know whether your approach works, but there is an easier solution.

您可以通过定义部分函数来传递多个参数.

You can pass multiple arguments by defining a partial function.

损失函数的输出是标量.

The output of a loss function is a scalar.

这里是一个示例，演示了如何将多个参数传递给损失函数:

Here is an example that demonstrates how to pass multiple arguments to a loss function:

from keras.layers import Input, Dense
from keras.models import Model
import keras.backend as K


def custom_loss(arg1, arg2):
    def loss(y_true, y_pred):
        # Use arg1 and arg2 here as you wish and return loss
        # For example:
        return K.mean(y_true - y_pred) + arg1 + arg2
    return loss

x = Input(shape=(1,))
arg1 = Input(shape=(1,))
arg2 = Input(shape=(1,))
out = Dense(1)(x)
model = Model([x, arg1, arg2], out)
model.compile('sgd', custom_loss(arg1, arg2))

这篇关于正确的损失函数方式的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！