CODEWITHSUNDEEP
keras
mona
mona

Reputation: 13

ValueError: Error when checking input: expected dense_1_input to have 2 dimensions

I have tried the following example:

from keras.models import Sequential  
from keras.layers import *  
import numpy as np

x_train = np.random.random((30,50,50,3))
y_train = np.random.randint(2, size=(30,1))

model = Sequential()    

#start from the first hidden layer, since the input is not         actually a layer   
#but inform the shape of the input, with 3 elements.    
model.add(Dense(units=4,input_shape=(3,))) #hidden layer 1    with input

#further layers:    
model.add(Dense(units=4)) #hidden layer 2
model.add(Dense(units=1)) #output layer

model.compile(loss='binary_crossentropy',
           optimizer='adam',
           metrics=['accuracy'])

model.fit(x_train, y_train,
       epochs=20,
       batch_size=128)
score = model.evaluate(x_test, y_test, batch_size=128)

I get this error:

ValueError: Error when checking input: expected dense_1_input to have 2 dimensions, but got array with shape (30, 50, 50, 3).

Thus, I changed the input_shape as follows:

from keras.models import Sequential  
from keras.layers import *  
import numpy as np

x_train = np.random.random((30,50,50,3))
y_train = np.random.randint(2, size=(30,1))

model = Sequential()    

#start from the first hidden layer, since the input is not         actually a layer   
#but inform the shape of the input, with 3 elements.    
model.add(Dense(units=4,input_shape=(50,50,3))) #hidden layer 1    with input

#further layers:    
model.add(Dense(units=4)) #hidden layer 2
model.add(Dense(units=1)) #output layer

model.compile(loss='binary_crossentropy',
           optimizer='adam',
           metrics=['accuracy'])

model.fit(x_train, y_train,
       epochs=20,
       batch_size=128)
score = model.evaluate(x_test, y_test, batch_size=128)

But now I get this error:

ValueError: Error when checking target: expected dense_2 to have 4 dimensions, but got array with shape (30, 1)

Any idea about what am I doing wrong?

Upvotes: 1

Views: 159

Answers (1)

Dulmina
Dulmina

Reputation: 527

the problem is with the output shape of the last dense layer. You can use model.summary() to see the output shape of each layer.

your output shape is (None,50,50,1),but to match with your y_train shape it should be in (None,1) shape.

So i suggest you to add a flattern layer before the last dense layer.Plese refer this link for the definition of flattern layer in keras.

This is how your model code should looks like

model.add(Dense(units=4,input_shape=(50,50,3),name="d1")) #hidden layer 1    with input  
model.add(Dense(units=4,name="d2")) #hidden layer 2
model.add(Flatten())
model.add(Dense(units=1,name="d3")) #output layer

model.compile(loss='binary_crossentropy',
           optimizer='adam',
           metrics=['accuracy'])

model.summary()

Futher more use name for your layers it will be easy for you to understand where the problem is.good luck ;-)

Upvotes: 1

Related Questions