浅谈keras中loss与val_loss的关系

蒸汽减温减压装置loss函数如何接受输⼊值

keras封装的⽐较厉害，官⽹给的例⼦写的云⾥雾⾥，

在stackoverflow到了

You can wrap the loss function as a inner function and pass your input tensor to it (as commonly done when passing additional arguments to the loss function).

def custom_loss_wrapper(input_tensor):

def custom_loss(y_true, y_pred):

return K.binary_crossentropy(y_true, y_pred) + K.mean(input_tensor)

return custom_loss

input_tensor = Input(shape=(10,))

hidden = Dense(100, activation='relu')(input_tensor)

out = Dense(1, activation='sigmoid')(hidden)

model = Model(input_tensor, out)

modelpile(loss=custom_loss_wrapper(input_tensor), optimizer='adam')

You can verify that input_tensor and the loss value will change as different X is passed to the model.

X = np.random.rand(1000, 10)

y = np.random.randint(2, size=1000)

X *= 1000

地沟油检测

fit_generator

fit_generator ultimately calls train_on_batch which allows for x to be a dictionary.

Also, it could be a list, in which casex is expected to map 1:1 to the inputs defined in Model(input=[in1, …], …)

### generator

yield [inputX_1,inputX_2],y

### model

model = Model(inputs=[inputX_1,inputX_2],outputs=...)

补充知识：学习keras时对loss函数不同的选择，则model.fit⾥的outputs可以是one_hot向量，也可以是整形标签

我就废话不多说了，⼤家还是直接看代码吧~

from __future__ import absolute_import, division, print_function, unicode_literals

import tensorflow as tf

from tensorflow import keras

import numpy as np

import matplotlib.pyplot as plt

print(tf.__version__)

fashion_mnist = keras.datasets.fashion_mnist

(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',

'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']

# plt.figure()

# plt.imshow(train_images[0])

# lorbar()

# id(False)

# plt.show()

train_images = train_images / 255.0

test_images = test_images / 255.0

# plt.figure(figsize=(10,10))

# for i in range(25):

# plt.subplot(5,5,i+1)

# icks([])

# id(False)

# plt.imshow(train_images[i], binary)

# plt.xlabel(class_names[train_labels[i]])主板清洗液

# plt.show()

model = keras.Sequential([

keras.layers.Flatten(input_shape=(28, 28)),

keras.layers.Dense(128, activation='relu'),机柜空调器

keras.layers.Dense(10, activation='softmax')

])

modelpile(optimizer='adam',

loss='categorical_crossentropy',

#loss = 'sparse_categorical_crossentropy' 则之后的label不需要变成one_hot向量，直接使⽤整形标签即可

metrics=['accuracy'])

one_hot_train_labels = _categorical(train_labels, num_classes=10)

model.fit(train_images, one_hot_train_labels, epochs=10)

one_hot_test_labels = _categorical(test_labels, num_classes=10)角关联

test_loss, test_acc = model.evaluate(test_images, one_hot_test_labels)

print('\nTest accuracy:', test_acc)

# predictions = model.predict(test_images)

狗皮护膝

# predictions[0]

# np.argmax(predictions[0])

# test_labels[0]

loss若为loss=‘categorical_crossentropy', 则fit中的第⼆个输出必须是⼀个one_hot类型，

⽽若loss为loss = ‘sparse_categorical_crossentropy' 则之后的label不需要变成one_hot向量，直接使⽤整形标签即可

以上这篇浅谈keras中loss与val_loss的关系就是⼩编分享给⼤家的全部内容了，希望能给⼤家⼀个参考，也希望⼤家多多⽀持。

本文发布于:2024-09-22 03:58:09，感谢您对本站的认可！

本文链接：https://www.17tex.com/tex/4/215945.html

上一篇：DBCC用法

下一篇：sqlserver安全管理之用户、角、架构与权限

标签：函数希望变成

留言与评论（共有 0 条评论）