Model was constructed with shape (None, 28) problem-CodePudding

I am getting an error. It says:

Model was constructed with shape (None, 28) for input KerasTensor(type_spec=TensorSpec(shape=(None, 28), dtype=tf.float32, name='dense_45_input'), name='dense_45_input', description="created by layer 'dense_45_input'"), but it was called on an input with incompatible shape (None, 28, 28).

Mycode is here:

from keras.utils import np_utils
from keras.datasets import mnist 
from keras.models import Sequential
from keras.layers import Dense, BatchNormalization, Dropout, Activation
import seaborn as sns
from keras.initializers import RandomNormal
from keras.initializers import he_normal
import matplotlib.pyplot as plt

(train_X, train_y), (test_X, test_y) = mnist.load_data()

output_dim = 10
input_dim = train_X.shape[1]

batch_size = 128
nb_epoch = 20

model_drop = Sequential()
model_drop.add(Dense(512, activation='relu', input_shape=(input_dim,),kernel_initializer=he_normal(seed=None)))
model_drop.add(BatchNormalization())
model_drop.add(Dropout(0.5))

model_drop.add(Dense(128, activation= 'relu', kernel_initializer=he_normal(seed=None)))
model_drop.add(BatchNormalization())
model_drop.add(Dropout(0.5))

model_drop.add(Dense(output_dim, activation = 'softmax'))

model_drop.summary()

model_drop.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

history = model_drop.fit(train_X, train_y, batch_size=batch_size, epochs=nb_epoch, verbose=1)

How can I fix this? Also I am adding error photo..

CodePudding user response：

Your input dimensions in building the dense layer are wrong, if the image is 28x28 you need to be able to receive all the pixels (i.e. you need 28*28=784 input connections). To really get this working you also need to one-hot encode the y variables as well as reshape the images.

(train_X, train_y), (test_X, test_y) = mnist.load_data()
output_dim = 10
input_dim = train_X.shape[1]

batch_size = 128
nb_epoch = 20

model_drop = Sequential()
# see input_dim edit here
model_drop.add(Dense(512, activation='relu', input_shape=(input_dim*input_dim,),kernel_initializer=he_normal(seed=None)))
model_drop.add(BatchNormalization())
model_drop.add(Dropout(0.5))

model_drop.add(Dense(128, activation= 'relu', kernel_initializer=he_normal(seed=None)))
model_drop.add(BatchNormalization())
model_drop.add(Dropout(0.5))

model_drop.add(Dense(output_dim, activation = 'softmax'))

model_drop.summary()
model_drop.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

# encode Y_train and also shape X_train so it can feed to dense layer
Y_train = np_utils.to_categorical(train_y, num_classes=10)
X_train = train_X.reshape((-1, 28*28))

history = model_drop.fit(X_train, Y_train, batch_size=batch_size, epochs=nb_epoch, verbose=1)