KeyError: 'acc' -> acc = History.history['acc']

Question

代码链接：https://colab.research.google.com/drive/1_a4PLwDiFhF7qVlX_vvwKM4QM4Dxu0L0?usp=sharing

import matplotlib.pyplot as plt

acc = history.history['acc']
val_acc = history.history['val_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']

epochs = range(1, len(acc) + 1)

# "bo" is for "blue dot"
plt.plot(epochs, loss, 'bo', label='Training loss')
# b is for "solid blue line"
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()

plt.show()

错误显示：

KeyError                                  Traceback (most recent call last)

<ipython-input-31-12e4df2349dc> in <module>
      1 import matplotlib.pyplot as plt
      2 
----> 3 acc = history.history['acc']
      4 val_acc = history.history['val_accuracy']
      5 loss = history.history['loss']

KeyError: 'acc'

您好，我已经尝试过使用 python -manning 进行深度学习的练习 3.5-classifying-movie-reviews.ipynb 并显示错误，请提供帮助吗？

Answer 1

示例：粗略绘制图表，在 MNST 数据库上使用一些简单的密集层来呈现所需的更多时间（仅 15 个时期）。

History 是您作为数组添加的字典或它创建为记录结果的训练，请在条件之前使用 model.fit() 或回调方法。

import os
from os.path import exists

import tensorflow as tf
import tensorflow_datasets as tfds

import matplotlib.pyplot as plt

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
Variables
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
RANDOM_STATE = 21
BATCH_SIZE = 16
EPOCHES = 15

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
DataSet
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
ds = tfds.load('mnist', split='train', shuffle_files=True)
ds = ds.shuffle(1024).batch(64).prefetch(tf.data.experimental.AUTOTUNE)
assert isinstance(ds, tf.data.Dataset)

for example in ds.take(1):
  image, label = example["image"], example["label"]

list_image = [ ]    
list_label = [ ]

list_image = tf.constant(image, shape=(64, 28, 28)).numpy()
list_label = tf.constant(label, shape=(64, 1, 1)).numpy()


samples=image.shape[0]

y_train = tf.random.uniform((samples, 1, 1), maxval=2, dtype=tf.int32)

model = tf.keras.models.Sequential([ ])
model.add(tf.keras.layers.Dense(64, activation='relu', input_shape=(28, 28, 1)))
model.add(tf.keras.layers.Dropout(0.18))
model.add(tf.keras.layers.Dense(32, activation='relu'))
model.add(tf.keras.layers.Dropout(0.15))
model.add(tf.keras.layers.Dense(1, activation='sigmoid'))

es = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=5) 

# Compiling the model
model.compile(loss='bce', optimizer='adam', metrics=['binary_accuracy'])

# Fitting the model
history = model.fit(list_image, y_train, batch_size = BATCH_SIZE, validation_data =(list_image, y_train), epochs = EPOCHES, callbacks=[es]) # verbose = 0

# Check out our train loss and test loss over epochs.
train_loss = history.history['loss']
test_loss = history.history['val_loss']
y_train = tf.constant(y_train, shape=(64, )).numpy()


print( test_loss )
print( y_train )



# Visualizing our training and testing loss by epoch
plt.figure(figsize=(10, 5))
plt.plot(train_loss, label='Training Loss', color='#185fad')
plt.plot(test_loss, label='Testing Loss', color='orange')
# plt.plot(y_train, label='y_train', color='blue')
plt.title('Training and Testing Loss by Epoch', fontsize = 20)
# plt.title('label input', fontsize = 20)
plt.xlabel('Epoch', fontsize = 11)
plt.xlabel('n', fontsize = 11)
plt.ylabel('Binary Crossentropy', fontsize = 11)
plt.legend(fontsize = 11)

plt.show()

input('...')

输出：

Answer 2

尝试打印历史记录中可用的密钥。

history.history.keys()

当前版本显示以下按键，请将

acc

替换为

accuracy

dict_keys(['accuracy', 'loss', 'val_accuracy', 'val_loss', 'learning_rate'])