英文:
Deep Learning with Python IMDB dataset
问题
在代码的末尾，您遇到了一个错误：“name 'acc' is not defined”。看起来是因为您在使用epochs变量而不是acc来定义范围。下面是修复后的代码：
import matplotlib.pyplot as plt
history_dict = history.history
loss_values = history_dict['loss']
val_loss_values = history_dict['val_loss']
epochs = range(1, len(loss_values) + 1) # 修复此行
plt.plot(epochs, loss_values, 'bo', label='Training loss')
plt.plot(epochs, val_loss_values, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.show()
这个更正会使用loss_values代替acc来定义epochs的范围。这应该修复您遇到的问题。
英文:
I am currently working through Chollet's "Deep Learning with Python." My neural network is running just fine but I am having an issue with plotting the training and validation loss> Here is the code:
from keras.datasets import imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(
num_words=10000)
max([max(sequence) for sequence in train_data])
word_index = imdb.get_word_index()
reverse_word_index = dict(
[(value, key) for (key, value) in word_index.items()])
decoded_review = ' '.join(
[reverse_word_index.get(i - 3, '?') for i in train_data[0]])
import numpy as np
def vectorize_sequences(sequences, dimension=10000):
results = np.zeros((len(sequences), dimension))
for i, sequence in enumerate(sequences):
results[i, sequence] = 1.
return results
x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)
y_train = np.asarray(train_labels).astype('float32')
y_test = np.asarray(test_labels).astype('float32')
from keras import models
from keras import layers
model = models.Sequential()
model.add(layers.Dense(16, activation='relu', input_shape=(10000,)))
model.add(layers.Dense(16, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))
from keras import optimizers
model.compile(optimizer=optimizers.RMSprop(learning_rate=0.001),
loss='binary_crossentropy',
metrics=['accuracy'])
x_val = x_train[:10000]
partial_x_train = x_train[10000:]
y_val = y_train[:10000]
partial_y_train = y_train[10000:]
model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['acc'])
history = model.fit(partial_x_train, partial_y_train, epochs=20, batch_size=512, validation_data=(x_val, y_val))
import matplotlib.pyplot as plt
history_dict = history.history
loss_values = history_dict['loss']
val_loss_values = history_dict['val_loss']
epochs = range(1, len(acc) + 1)
plt.plot(epochs, loss_values, 'bo', label='Training loss')
plt.plot(epochs, val_loss_values, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.show()
Toward the end, I am getting a "name 'acc' is not defined" error. Not sure why this is the case as I am following exactly what Chollet has in the textbook.
答案1
得分: 0
epochs = range(1, len(acc) + 1) 似乎没有特定含义。我猜这是错误写的。
要获得绘图所需的输出，您需要创建一个包含 x 轴值的列表，这些值由周期数决定。
所以下面是完整的代码：
from keras.datasets import imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(
num_words=10000)
max([max(sequence) for sequence in train_data])
word_index = imdb.get_word_index()
reverse_word_index = dict(
[(value, key) for (key, value) in word_index.items()])
decoded_review = ' '.join(
[reverse_word_index.get(i - 3, '?') for i in train_data[0]])
import numpy as np
def vectorize_sequences(sequences, dimension=10000):
results = np.zeros((len(sequences), dimension))
for i, sequence in enumerate(sequences):
results[i, sequence] = 1.
return results
x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)
y_train = np.asarray(train_labels).astype('float32')
y_test = np.asarray(test_labels).astype('float32')
from keras import models
from keras import layers
model = models.Sequential()
model.add(layers.Dense(16, activation='relu', input_shape=(10000,)))
model add(layers.Dense(16, activation='relu'))
model add(layers.Dense(1, activation='sigmoid'))
from keras import optimizers
model.compile(optimizer=optimizers.RMSprop(learning_rate=0.001),
loss='binary_crossentropy',
metrics=['accuracy'])
x_val = x_train[:10000]
partial_x_train = x_train[10000:]
y_val = y_train[:10000]
partial_y_train = y_train[10000:]
model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['acc'])
epochs = 20
history = model.fit(partial_x_train, partial_y_train, epochs=epochs, batch_size=512, validation_data=(x_val, y_val))
import matplotlib.pyplot as plt
history_dict = history.history
loss_values = history_dict['loss']
val_loss_values = history_dict['val_loss']
x_axis = [i for i in range(1,epochs+1)]
plt.plot(x_axis, loss_values, 'bo', label='Training loss')
plt.plot(x_axis, val_loss_values, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.show()
希望这对您有所帮助。
英文:
epochs = range(1, len(acc) + 1) doesn't seem to stand for anything. I guess this is written by mistake.
To get the desired output for the plot, you need to create a list that contains values for the x-axis, which is determined by the number of epochs.
So this should be the full code:
from keras.datasets import imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(
num_words=10000)
max([max(sequence) for sequence in train_data])
word_index = imdb.get_word_index()
reverse_word_index = dict(
[(value, key) for (key, value) in word_index.items()])
decoded_review = ' '.join(
[reverse_word_index.get(i - 3, '?') for i in train_data[0]])
import numpy as np
def vectorize_sequences(sequences, dimension=10000):
results = np.zeros((len(sequences), dimension))
for i, sequence in enumerate(sequences):
results[i, sequence] = 1.
return results
x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)
y_train = np.asarray(train_labels).astype('float32')
y_test = np.asarray(test_labels).astype('float32')
from keras import models
from keras import layers
model = models.Sequential()
model.add(layers.Dense(16, activation='relu', input_shape=(10000,)))
model.add(layers.Dense(16, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))
from keras import optimizers
model.compile(optimizer=optimizers.RMSprop(learning_rate=0.001),
loss='binary_crossentropy',
metrics=['accuracy'])
x_val = x_train[:10000]
partial_x_train = x_train[10000:]
y_val = y_train[:10000]
partial_y_train = y_train[10000:]
model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['acc'])
epochs = 20
history = model.fit(partial_x_train, partial_y_train, epochs=epochs, batch_size=512, validation_data=(x_val, y_val))
import matplotlib.pyplot as plt
history_dict = history.history
loss_values = history_dict['loss']
val_loss_values = history_dict['val_loss']
x_axis = [i for i in range(1,epochs+1)]
plt.plot(x_axis, loss_values, 'bo', label='Training loss')
plt.plot(x_axis, val_loss_values, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.show()
通过集体智慧和协作来改善编程学习和解决问题的方式。致力于成为全球开发者共同参与的知识库，让每个人都能够通过互相帮助和分享经验来进步。
评论