0

The below source code works fine.

# The encoding process
input_img = Input(shape=(img_cols, img_cols, 1))
x = Conv2D(16, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D(pool_size = (2, 2), padding='same')(x)
x = Conv2D( 8, kernel_size = (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D(pool_size = (2, 2), padding='same')(x)
x = Conv2D( 8, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D(pool_size = (2, 2), padding='same')(x)

x1 = Conv2D(8, (3, 3), activation='relu', padding='same')(encoded)   ### 
x = UpSampling2D((2, 2))(x1)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(16, (3, 3), activation='relu')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)

autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
autoencoder.fit(x_train, x_train, epochs=10, batch_size=128, shuffle=True) #

However, i want to separate code model from decoding model like the following:

encoder=Model(inputs=input_img, outputs=encoded)
decoder=Model(inputs=x1,outputs=decoded )
autoencoder_outputs = decoder(encoder(input_img))
autoencoder= Model(input_img, autoencoder_outputs, name='AE')
autoencoder.summary()

It doesn't work for me. I am new in keras and python

i get the following error:

Graph disconnected: cannot obtain value for tensor Tensor("input_13:0", shape=(None, 28, 28, 1), dtype=float32) at layer "input_13". The following previous layers were accessed without issue: []

Improve this question

2 Answers 2

Reset to default
1

This is your updated reproducible code:

Your input shapes were all wrongly placed. In the bottolneck, you were passing a tensor with shape (8,8,8). You can get an idea from the summary().

from tensorflow.keras.layers import *
from tensorflow.keras.models import *
import numpy as np
# The encoding process

img_cols = 64

input_img = Input(shape=(img_cols, img_cols, 1))
x = Conv2D(16, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D(pool_size = (2, 2), padding='same')(x)
x = Conv2D( 8, kernel_size = (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D(pool_size = (2, 2), padding='same')(x)
x = Conv2D( 8, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D(pool_size = (2, 2), padding='same')(x)

x1 = Conv2D(8, (3, 3), activation='relu', padding='same')(encoded)   ### 
x = UpSampling2D((2, 2))(x1)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(16, (3, 3), activation='relu', padding = 'same')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)

autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')

autoencoder.summary()
x_train = np.zeros((10,64,64,1))
y_train =  np.zeros((10,64,64,1))
autoencoder.fit(x_train, x_train, epochs=10, batch_size=128, shuffle=True) 

# second approach

input_img = Input(shape=(img_cols, img_cols, 1))
x = Conv2D(16, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D(pool_size = (2, 2), padding='same')(x)
x = Conv2D( 8, kernel_size = (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D(pool_size = (2, 2), padding='same')(x)
x = Conv2D( 8, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D(pool_size = (2, 2), padding='same')(x)

reduced_dim = 8
filters = 8
input_decoder = Input(shape = (reduced_dim, reduced_dim, 8) )
x1 = Conv2D(8, (3, 3), activation='relu', padding='same')(input_decoder)   ### 
x = UpSampling2D((2, 2))(x1)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(16, (3, 3), activation='relu', padding = 'same')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)

encoder=Model(inputs=input_img, outputs=encoded)
decoder=Model(inputs=input_decoder, outputs=decoded )
autoencoder_outputs = decoder(encoder(input_img))
autoencoder= Model(input_img, autoencoder_outputs, name='AE')
autoencoder.summary()

Model: "model_9"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_10 (InputLayer)        [(None, 64, 64, 1)]       0         
_________________________________________________________________
conv2d_49 (Conv2D)           (None, 64, 64, 16)        160       
_________________________________________________________________
max_pooling2d_21 (MaxPooling (None, 32, 32, 16)        0         
_________________________________________________________________
conv2d_50 (Conv2D)           (None, 32, 32, 8)         1160      
_________________________________________________________________
max_pooling2d_22 (MaxPooling (None, 16, 16, 8)         0         
_________________________________________________________________
conv2d_51 (Conv2D)           (None, 16, 16, 8)         584       
_________________________________________________________________
max_pooling2d_23 (MaxPooling (None, 8, 8, 8)           0         
_________________________________________________________________
conv2d_52 (Conv2D)           (None, 8, 8, 8)           584       
_________________________________________________________________
up_sampling2d_21 (UpSampling (None, 16, 16, 8)         0         
_________________________________________________________________
conv2d_53 (Conv2D)           (None, 16, 16, 8)         584       
_________________________________________________________________
up_sampling2d_22 (UpSampling (None, 32, 32, 8)         0         
_________________________________________________________________
conv2d_54 (Conv2D)           (None, 32, 32, 16)        1168      
_________________________________________________________________
up_sampling2d_23 (UpSampling (None, 64, 64, 16)        0         
_________________________________________________________________
conv2d_55 (Conv2D)           (None, 64, 64, 1)         145       
=================================================================
Total params: 4,385
Trainable params: 4,385
Non-trainable params: 0
_________________________________________________________________
Epoch 1/10
1/1 [==============================] - 0s 1ms/step - loss: 0.6931
Epoch 2/10
1/1 [==============================] - 0s 1ms/step - loss: 0.6931
Epoch 3/10
1/1 [==============================] - 0s 1ms/step - loss: 0.6931
Epoch 4/10
1/1 [==============================] - 0s 1ms/step - loss: 0.6931
Epoch 5/10
1/1 [==============================] - 0s 1ms/step - loss: 0.6931
Epoch 6/10
1/1 [==============================] - 0s 1ms/step - loss: 0.6931
Epoch 7/10
1/1 [==============================] - 0s 1ms/step - loss: 0.6931
Epoch 8/10
1/1 [==============================] - 0s 1ms/step - loss: 0.6931
Epoch 9/10
1/1 [==============================] - 0s 2ms/step - loss: 0.6931
Epoch 10/10
1/1 [==============================] - 0s 2ms/step - loss: 0.6931
Model: "AE"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_11 (InputLayer)        [(None, 64, 64, 1)]       0         
_________________________________________________________________
model_10 (Model)             (None, 8, 8, 8)           1904      
_________________________________________________________________
model_11 (Model)             (None, 64, 64, 1)         2481      
=================================================================
Total params: 4,385
Trainable params: 4,385
Non-trainable params: 0
Improve this answer
Sign up to request clarification or add additional context in comments.

5 Comments

Thank you so much for the help, @furcifer when i run the fit command it appear the following error: Error when checking target: expected model_37 to have shape (32, 32, 1) but got array with shape (28, 28, 1) I have image database shaped to 28x28, how can i adapt the code to that ? Thanks in advance
Don't choose 28, resize your inputs to have shape 32, the reason is you are applying max pooling and upsampling. So, 28 is not a power of 2, the model will have different input and output shape.
Yes, i noticed that, i change it to 64, it does perfect works. but it does works before separation with 28x28, any clue ?? @furcifer
Because your model can't reproduce the shapes, you can look into summary. When using max-pooling and upsampling in a model, always use the input size as a power of 2 (considering pooling kernel has size 2).
ok , thank you so much, i resize it to 32, it does works fine. i appreciate your help.
1

A model must have a keras.layers.Input for inputs.

decoder=Model(inputs=x1,outputs=decoded )

Here, x1 is not an Input. It is connected to the encoder graph, hence this error.

Improve this answer

Comments

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.