Keras自定义损失函数不打印张量值 [英] Keras custom loss function not printing value of tensor

问题描述

我正在编写一个简单的损失函数，其中我必须将张量转换为numpy数组(这是必不可少的).我只是想打印张量的值，但出现此错误:-

I am writing just a simple loss function in which I have to convert the tensor to numpy array(it's essential). I am just trying to print value of the tensor but I am getting this error:-

Tensor("loss/activation_4_loss/Print:0"，shape =(?, 224，224，2)， dtype = float32)

Tensor("loss/activation_4_loss/Print:0", shape=(?, 224, 224, 2), dtype=float32)

def Lc(y_true, y_pred):
    x=K.print_tensor(y_pred)
    print(x)
    return K.mean(y_pred)

请告诉我如何从张量中获取值(数字)?我也尝试过"eval"，但它也引发了一个严重的错误，即没有会话存在，并且它是一个占位符等.整个程序执行得很好，只是" print_tensor "行引起了问题. /p>

Kindly tell me that how can I get the value(numerics) from the tensor? I also tried "eval" but it also threw a big fat error about no session is there and it is a placeholder etc. The whole program is executing fine, just "print_tensor" line is causing problem.

推荐答案

print语句是多余的. print_tensor将已经打印出这些值.

The print statement is redundant. print_tensor will already print the values.

来自print_tensor的文档:

From the documentation of print_tensor:

"请注意，print_tensor返回与x相同的新张量 应在以下代码中使用.否则 评估期间不会考虑打印操作."

"Note that print_tensor returns a new tensor identical to x which should be used in the following code. Otherwise the print operation is not taken into account during evaluation."

在上面的代码中，由于将y_pred分配给x，并且不再使用x，所以打印失败.

In the code above, since y_pred was assigned to x and x was no longer used, the print failed.

使用以下版本.

def Lc(y_true, y_pred):
    y_pred=K.print_tensor(y_pred)
    return K.mean(y_pred)

---

def cat_loss(y_true, y_pred):
    y_pred = K.print_tensor(y_pred)
    return K.categorical_crossentropy(y_true, y_pred)

将这个cat_loss函数放入训练循环后，我可以看到如下输出:

After I put this cat_loss function in my training loop, I can see the output like this:

[[0.000191014129 0.230871275 0.43813318] ...]

[[0.000191014129 0.230871275 0.43813318]...]

190/255 [===================> ........]-ETA:0s-损失:0.3442-acc:0.9015

190/255 [=====================>........] - ETA: 0s - loss: 0.3442 - acc: 0.9015

[[3.16367514e-05 1.70419597e-07 0.000147014405] ...]

[[3.16367514e-05 1.70419597e-07 0.000147014405]...]

这篇关于Keras自定义损失函数不打印张量值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！