ValueError：检查输入时出错：预期的dense_10_input有2维，但得到了形状为（60000、28、28）的数组

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所述的错误它 给我一个错误说：“ValueError：检查输入时出错： 预计 dense_7_input 有 2 维，但得到了形状的数组 (60000, 28, 28)”，我不知道为什么。我检查了以前的答案 解决这个问题，但没有任何效果。 新：所以当我尝试最后一段代码时，它给了我这个错误： ValueError：输入数组的样本数应与目标数组相同。找到 60000 个输入样本和 10000 个目标样本。

enter image description here

# 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)

# 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()

# 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
model = Sequential()
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)

# New one #######
# 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

我查看了您的代码，并让它工作。我添加了 flatten 层，它将输入转换为可行的格式。我还使用 tensorflow.keras 而不是 keras，因为我认为那个版本更好，但你可以同时使用它。您的类型也有问题，所以我将您的 X_train 和 X_test 更改为 float32 类型的 numpy 数组。

# Imports
import tensorflow
from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.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)

# Imports
import tensorflow
from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense,Flatten
from tensorflow.keras.utils import to_categorical
import numpy as np
# Configuration options
feature_vector_length = 784
num_classes = 60000

# 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}')
X_train=np.array(X_train,dtype="float32")
X_test=np.array(X_train,dtype="float32")
# Create the model
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)