使用 keras 的时尚 MNIST

Question

Code:

import keras.datasets.fashion_mnist as fashion_mnist
import keras
import matplotlib.pyplot as plt
from keras.utils import np_utils
from sklearn.model_selection import train_test_split
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data() 
xtrain, xvalid, ytrain, yvalid = train_test_split(train_images, train_labels, test_size=0.33, shuffle= True)

xtrain = xtrain / 255.0
xvalid =  xvalid/255.0
ytrain = np_utils.to_categorical(ytrain )
yvalid = np_utils.to_categorical(yvalid)

history_dict = history.history
print(history_dict.keys())

history=model1.fit(train_images, train_labels, epochs=30, batch_size=64)

loss = history.history['loss']
val_loss = history.history['val_loss']

accuracy = history.history['binary_accuracy']
val_accuracy = history.history['val_accuracy']

plt.plot(history.history['accuracy'])  
plt.plot(history.history['val_accuracy'])
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.show()

I get the following result,: KeyError: 'val_accuracy ' ,, I use google.colab. dict_keys(['loss', 'accuracy']) google.colab. dict_keys(['loss', 'accuracy']) , only two variables are available. how to reach val_accuracy and val_loss?

Any suggestions would be appreciated

Answer 1

To need to have val_accuracy and val_loss , you need to supply validation data to the model.fit . Try this:

history = model1.fit(train_images, train_labels, 
                  validation_data = (xvalid,yvalid), 
                  epochs=30, batch_size=64)