Skip to main content
 首页 » 编程设计

python之在深度学习keras中为损失函数添加中间层

2024年12月31日14dflying

我想在 keras 中为 DNN 模型 VAE 使用使用中间层的自定义损失函数。我调用模型函数,然后将损失添加到层中。

错误是:

ValueError: An operation has `None` for gradient. Please make sure that all of your ops have a gradient defined (i.e. are differentiable). Common ops without gradient: K.argmax, K.round, K.eval 

model 已编译但在训练期间导致错误

#Below is the code which causes error 
#this returns the models (en,de, model) and layers (z_mean and #z_log_sigma) 
en,de,model,z_mean,z_log_sigma = load_model(config) 
#defining loss using intermediate layers returned 
kl_loss = - 0.5 * K.mean(1 + z_log_sigma - K.square(z_mean) -  
                      K.exp(z_log_sigma), axis=-1) 
 
model.add_loss(kl_loss) 
model.compile( optimizer=optimizer) 
#error is raised during training  
history = model.fit_generator( 
                    genfun, 
                    steps_per_epoch = display_interval, 
                    epochs = 1, 
                    shuffle=False, 
                    verbose = 1 
                ) #callbacks=[eval_map])     

请您参考如下方法:

此解决方案适用于设计自定义损失层。

en,de,model,z_mean,z_log_sigma = load_model(config) 
 
def custom_loss_wrapper(z_mean=z_mean,z_log_sigma=z_log_sigma): 
    def loss(y_true, y_pred): 
        xent_loss = binary_crossentropy(y_true, y_pred) 
        kl_loss = - 0.5 * K.mean(1 + z_log_sigma - K.square(z_mean) -  
                    K.exp(z_log_sigma), axis=-1) 
        return  xent_loss+kl_loss 
    return loss 
model.compile(  
optimizer=optimizer,loss=custom_loss_wrapper(z_mean,z_log_sigma))