Keras functional CNN model gets error: graph disconnected at main input layer

0
votes

I am developing a functional Keras model for CNN with 1d input layers in R.

When I run the keras_model function to build the model I get the following error:

Error in py_call_impl(callable, dots$args, dots$keywords) : ValueError: Graph disconnected: cannot obtain value for tensor Tensor("main_input_15:0", shape=(4201, 1024), dtype=float32) at layer "main_input". The following previous layers were accessed without issue: []

Detailed traceback: File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/keras/legacy/interfaces.py", line 91, in wrapper return func(*args, **kwargs) File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/keras/engine/network.py", line 93, in init self._init_graph_network(*args, **kwargs) File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/keras/engine/network.py", line 231, in _init_graph_network self.inputs, self.outputs) File "/Library/Frameworks/Python.framew

I am attaching my code, any help would be really appreciated.

main_input = layer_input(shape = c(1024), batch_shape = c(4201,1024), dtype = 'float32', name = 'main_input') %>%
  layer_reshape( target_shape = list(1024,1), input_shape = c(1024),dtype = 'float32', batch_input_shape = c(4201, 1024), batch_size = 4201)

conv1 = layer_conv_1d(filters = 64, kernel_size = 10, strides = 5, dtype = 'float32', activation = 'relu' )
max1 = layer_max_pooling_1d(pool_size = 10)

first_conv = main_input %>% conv1%>%max1

conv2 = layer_conv_1d(filters = 32, kernel_size = 5, strides = 3, dtype = 'float32', activation = 'relu' )
max2 = layer_max_pooling_1d(pool_size = 5)

second_conv = first_conv %>% conv2 %>% max2

conc1 = second_conv %>% layer_flatten()

semantic_input = layer_input(shape = c(2074), dtype = 'float32', batch_shape = c(4201,2074),  name = 'semantic_input')%>%
  layer_reshape(target_shape = list(2074,1), input_shape = c (2074), dtype = 'float32')

conc2 = semantic_input %>% layer_flatten()

output = layer_concatenate(c(conc1, conc2)) %>%
  layer_dense( units = 100, activation = 'relu', use_bias = TRUE) %>%
  layer_dense(units = 50, activation = 'relu', use_bias = TRUE) %>%
  layer_dense(units = 25, activation = 'relu', use_bias = TRUE)%>%
  layer_dense(units = 10, activation = 'relu', use_bias = TRUE)%>%
  layer_dense(units = 1, activation = 'softmax', name = 'output')


cnn1_model = keras_model(
  inputs = c(main_input,semantic_input),
  outputs = c(output)
)

I get the above mentioned error in the last line of this code when i try to build the model.

1
rkerasconv-neural-network

1 Answers

0
votes

I have figured it out, after 2 days of blockade!

Both the input layers should not be reshaped when they are defined. The reshaping can be carried on in next step, the input layers should be independently declared.

following is the fixed code:

main_input = layer_input(shape = c(1024), batch_shape = c(4201,1024), dtype = 'float32', name = 'main_input') 

main_reshaped = main_input %>% layer_reshape( target_shape = list(1024,1), input_shape = c(1024),dtype = 'float32', batch_input_shape = c(4201, 1024), batch_size = 4201)

conv1 = layer_conv_1d(filters = 64, kernel_size = 10, strides = 5, dtype = 'float32', activation = 'relu' )
max1 = layer_max_pooling_1d(pool_size = 10)

conv2 = layer_conv_1d(filters = 32, kernel_size = 5, strides = 3, dtype = 'float32', activation = 'relu' )
max2 = layer_max_pooling_1d(pool_size = 5)

conv = reshaped %>% conv1%>%max1%>%conv2 %>% max2 %>% layer_flatten()

semantic_input = layer_input(shape = c(2074), dtype = 'float32', batch_shape = c(4201,2074),  name = 'semantic_input')


sem_reshaped = semantic_input %>% layer_reshape(target_shape = list(2074,1), input_shape = c (2074), dtype = 'float32')

conc = sem_reshaped %>% layer_flatten()

output = layer_concatenate(c(conv, conc)) %>%
  layer_dense( units = 100, activation = 'relu', use_bias = TRUE) %>%
  layer_dense(units = 50, activation = 'relu', use_bias = TRUE) %>%
  layer_dense(units = 25, activation = 'relu', use_bias = TRUE)%>%
  layer_dense(units = 10, activation = 'relu', use_bias = TRUE)%>%
  layer_dense(units = 1, activation = 'softmax', name = 'output')

cnn1_model = keras_model(
  inputs = c(main_input,semantic_input),
  outputs = c(output)
)

so the model looks like this 

summary (cnn1_model)

_______________________________________________________________________________________________________________________________________________________________________________
Layer (type)                                             Output Shape                           Param #              Connected to                                              
===============================================================================================================================================================================
main_input (InputLayer)                                  (4201, 1024)                           0                                                                              
_______________________________________________________________________________________________________________________________________________________________________________
reshape_25 (Reshape)                                     (4201, 1024, 1)                        0                    main_input[0][0]                                          
_______________________________________________________________________________________________________________________________________________________________________________
conv1d_65 (Conv1D)                                       (4201, 203, 64)                        704                  reshape_25[0][0]                                          
_______________________________________________________________________________________________________________________________________________________________________________
max_pooling1d_50 (MaxPooling1D)                          (4201, 20, 64)                         0                    conv1d_65[6][0]                                           
_______________________________________________________________________________________________________________________________________________________________________________
conv1d_66 (Conv1D)                                       (4201, 6, 32)                          10272                max_pooling1d_50[6][0]                                    
_______________________________________________________________________________________________________________________________________________________________________________
semantic_input (InputLayer)                              (4201, 2074)                           0                                                                              
_______________________________________________________________________________________________________________________________________________________________________________
max_pooling1d_51 (MaxPooling1D)                          (4201, 1, 32)                          0                    conv1d_66[5][0]                                           
_______________________________________________________________________________________________________________________________________________________________________________
reshape_26 (Reshape)                                     (4201, 2074, 1)                        0                    semantic_input[0][0]                                      
_______________________________________________________________________________________________________________________________________________________________________________
flatten_35 (Flatten)                                     (4201, 32)                             0                    max_pooling1d_51[5][0]                                    
_______________________________________________________________________________________________________________________________________________________________________________
flatten_36 (Flatten)                                     (4201, 2074)                           0                    reshape_26[0][0]                                          
_______________________________________________________________________________________________________________________________________________________________________________
concatenate_38 (Concatenate)                             (4201, 2106)                           0                    flatten_35[0][0]                                          
                                                                                                                     flatten_36[0][0]                                          
_______________________________________________________________________________________________________________________________________________________________________________
dense_77 (Dense)                                         (4201, 100)                            210700               concatenate_38[0][0]                                      
_______________________________________________________________________________________________________________________________________________________________________________
dense_78 (Dense)                                         (4201, 50)                             5050                 dense_77[0][0]                                            
_______________________________________________________________________________________________________________________________________________________________________________
dense_79 (Dense)                                         (4201, 25)                             1275                 dense_78[0][0]                                            
_______________________________________________________________________________________________________________________________________________________________________________
dense_80 (Dense)                                         (4201, 10)                             260                  dense_79[0][0]                                            
_______________________________________________________________________________________________________________________________________________________________________________
output (Dense)                                           (4201, 1)                              11                   dense_80[0][0]                                            
===============================================================================================================================================================================
Total params: 228,272
Trainable params: 228,272
Non-trainable params: 0
_______________________________________________________________________________________________________________________________________________________________________________