浅谈keras中loss与val_loss的关系

2020-06-22 17:59 来源:易采站长站 作者:于海丽 点击: 评论:

A-A+

原标题:浅谈keras中loss与val_loss的关系

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找到了答案

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)
model.compile(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)
model.test_on_batch(X, y) # => 1.1974642

X *= 1000
model.test_on_batch(X, y) # => 511.15466

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])
# plt.colorbar()
# plt.grid(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)
#  plt.xticks([])
#  plt.yticks([])
#  plt.grid(False)
#  plt.imshow(train_images[i], cmap=plt.cm.binary)
#  plt.xlabel(class_names[train_labels[i]])
# plt.show()

model = keras.Sequential([
 keras.layers.Flatten(input_shape=(28, 28)),
 keras.layers.Dense(128, activation='relu'),
 keras.layers.Dense(10, activation='softmax')
])

model.compile(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 = keras.utils.to_categorical(train_labels, num_classes=10)

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

one_hot_test_labels = keras.utils.to_categorical(test_labels, num_classes=10)
test_loss, test_acc = model.evaluate(test_images, one_hot_test_labels)

print('\nTest accuracy:', test_acc)

# predictions = model.predict(test_images)
# predictions[0]
# np.argmax(predictions[0])
# test_labels[0]

【易采站长站编辑:秋军】