mnistデータの可視化

ValueError                                Traceback (most recent call last)
<ipython-input-44-4a873dc32b85> in <module>()
      2 plt.figure(figsize=(6,3))
      3 plt.subplot(1,2,1)
----> 4 plot_image(i, predict, test_label, test_image)
      5 plt.subplot(1,2,2)
      6 plot_value_array(i, predict,  test_label)

<ipython-input-42-6b66f0ca2cb5> in plot_image(i, predictions_array, true_label, img)
      8 
      9     predicted_label = np.argmax(predictions_array)
---> 10     if predicted_label == true_label:
     11         color = 'blue'
     12     else:

ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

←入力するとソースコードにシンタックスハイライトが付きます
import tensorflow as tf
import numpy as np
import sklearn
import matplotlib.pyplot as plt
import pandas as pd

from tensorflow import keras

from keras.layers import Dense, LSTM,Flatten

from keras.datasets import mnist

(train_image,train_label),(test_image,test_label) = mnist.load_data()



"""データの確認"""

train_image.shape#28*28のデータ

train_label.shape#60000のラベル

plt.figure()
plt.imshow(test_image[0])
plt.colorbar()
plt.grid(False)
plt.show()

type(train_image)

df = pd.DataFrame(train_label)

df.describe()

df.info()

from keras import models
from keras.layers import Dense

model = models.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",
        metrics=["accuracy"]
    )
model.summary()

train_image = train_image.astype("float32")/255
test_image = test_image.astype("float32")/255

test_image = test_image.reshape(10000,28,28)
train_image = train_image.reshape(60000,28,28)

from keras.utils import to_categorical

train_label = to_categorical(train_label)
test_label = to_categorical(test_label)

train_label.shape

history=model.fit(train_image,train_label,epochs=5)

test_loss, test_acc = model.evaluate(test_image,  test_label, verbose=2)

print('\nTest accuracy:', test_acc)

predict = model.predict(test_image)

np.argmax(predict[0])

np.argmax(test_label[0])

def plot_image(i, predictions_array, true_label, img):
    predictions_array, true_label, img = predictions_array[i], true_label[i], img[i]
    plt.grid(False)
    plt.xticks([])
    plt.yticks([])

    plt.imshow(img, cmap=plt.cm.binary)

    predicted_label = np.argmax(predictions_array)
    if predicted_label == true_label:
        color = 'blue'
    else:
        color = 'red'

    plt.xlabel("{} {:2.0f}% ({})".format(class_names[predicted_label],
                                    100*np.max(predictions_array),
                                    class_names[true_label]),
                                    color=color)

def plot_value_array(i, predictions_array, true_label):
    predictions_array, true_label = predictions_array[i], true_label[i]
    plt.grid(False)
    plt.xticks([])
    plt.yticks([])
    thisplot = plt.bar(range(10), predictions_array, color="#777777")
    plt.ylim([0, 1]) 
    predicted_label = np.argmax(predictions_array)

    thisplot[predicted_label].set_color('red')
    thisplot[true_label].set_color('blue')

predict

i = 0
plt.figure(figsize=(6,3))
plt.subplot(1,2,1)
plot_image(i, predict, test_label, test_image)
plt.subplot(1,2,2)
plot_value_array(i, predict,  test_label)
plt.show()

plt.figure(figsize=(6,3))
plt.subplot(1,2,1)
plot_image(i, predict, test_label, test_image)
plt.subplot(1,2,2)
plot_value_array(i, predict,  test_label)
plt.show()