ValueError：输入数组应具有与目标数组相同数量的样本。找到 60000 个输入样本和 10000 个目标样本

Question

我正在尝试训练我的深度神经网络识别手写 数字，但我不断收到标题中前面所述的错误它 给我一个错误说：ValueError：输入数组应该有 与目标数组相同数量的样本。找到 60000 个输入样本和 10000 个目标样本。我怎样才能解决这个问题？ （我已经尝试过 train_test_split 和运输，但没有任何效果）

# Imports
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.utils import to_categorical

 # Configuration options
 feature_vector_length = 784
 num_classes = 60000

 # Load the data
 (X_train, Y_train), (X_test, Y_test) = mnist.load_data()

 # Reshape the data - MLPs do not understand such things as '2D'.
 # Reshape to 28 x 28 pixels = 784 features
 X_train = X_train.reshape(X_train.shape[0], feature_vector_length)
 X_test = X_test.reshape(X_test.shape[0], feature_vector_length)

 # Convert into greyscale
 X_train = X_train.astype('float32')
 X_test = X_test.astype('float32')
 X_train /= 255
 X_test /= 255

 # Convert target classes to categorical ones
 Y_train = to_categorical(Y_train, num_classes)
 Y_test = to_categorical(Y_test, num_classes)

 # Load the data
 (X_train, Y_train), (X_test, Y_test) = mnist.load_data()

 # Visualize one sample
 import matplotlib.pyplot as plt
 plt.imshow(X_train[0], cmap='Greys')
 plt.show()

 # Set the input shape
 input_shape = (feature_vector_length,)
 print(f'Feature shape: {input_shape}')

# Create the model
# Using sigmoid instead of relu function
model = Sequential()
model.add(Flatten())
model.add(Dense(350, input_shape=input_shape, activation="sigmoid", 
kernel_initializer=init))
model.add(Dense(50, activation="sigmoid", kernel_initializer=init))
model.add(Dense(num_classes, activation="sigmoid", 
kernel_initializer=init))

# Configure the model and start training
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics= 
['accuracy'])
model.fit(X_train, Y_train, epochs=10, batch_size=250, verbose=1, 
validation_split=0.2)

# Test the model after training
test_results = model.evaluate(X_test, Y_test, verbose=1)
print(f'Test results - Loss: {test_results[0]} - Accuracy: 
{test_results[1]}%')

Answer 1

如果你想解决你的问题，这里是：

# Imports
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Flatten
from keras.utils import to_categorical

 # Configuration options
feature_vector_length = 784
num_classes = 10

# Load the data
(X_train, Y_train), (X_test, Y_test) = mnist.load_data()

# Reshape the data - MLPs do not understand such things as '2D'.
# Reshape to 28 x 28 pixels = 784 features
# X_train = X_train.reshape(X_train.shape[0], feature_vector_length)
# X_test = X_test.reshape(X_test.shape[0], feature_vector_length)

# Convert into greyscale
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255

# Convert target classes to categorical ones
Y_train = to_categorical(Y_train, num_classes)
Y_test = to_categorical(Y_test, num_classes)



# Create the model
# Using sigmoid instead of relu function
model = Sequential()
model.add(Flatten())
model.add(Dense(350, input_shape=input_shape, activation="relu"))
model.add(Dense(50, activation="relu"))
model.add(Dense(num_classes, activation="softmax"))

# Configure the model and start training
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics= 
['accuracy'])
model.fit(X_train, Y_train, epochs=10, batch_size=250, verbose=1, 
validation_split=0.2)

# Test the model after training
test_results = model.evaluate(X_test, Y_test, verbose=1)

但是您真的应该做一些研究并了解代码中的每一行应该做什么以及每个参数的含义。例如，sigmoid 激活函数的选择是错误的，尤其是在最后一层是首先要理解的。这是您应该研究的许多事情之一。然后是：

1. 了解为什么以及何时重塑您的数据，
2. flatten layer的目的是什么
3. 最重要的是，了解什么是 num_classes 以及为什么它是 10 而不是 1000 或 60000