Функциональная Keras Модель CNN получает ошибку: граф отключен на основном входном слое - PullRequest
Новая
       16

Функциональная Keras Модель CNN получает ошибку: граф отключен на основном входном слое

0 голосов
/ 06 апреля 2019

Я занимаюсь разработкой функциональной модели Keras для CNN с 1d входными слоями в R.

Когда я запускаю функцию keras_model для построения модели, я получаю следующую ошибку:

Ошибка в py_call_impl (вызываемый, точки $ args, точки $ ключевые слова): ValueError: График отключен: невозможно получить значение для тензорного тензора ("main_input_15: 0", shape = (4201, 1024), dtype = float32) на уровне "main_input". Следующие предыдущие слои были доступны без проблем: []

Подробный возврат: Файл "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/keras/legacy/interfaces.py", строка 91, в оболочке return func (* args, ** kwargs) Файл "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/keras/engine/network.py", строка 93, в init self._init_graph_network (* args, ** kwargs) Файл "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/keras/engine/network.py", строка 231, в _init_graph_network self.inputs, self.outputs) Файл "/Library/Frameworks/Python.framew

Я прилагаю свой код, любая помощь будет очень признательна. 

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)
)

Я получаю вышеупомянутую ошибку в последней строке этого кода, когда пытаюсь построить модель.

1 Ответ

0 голосов
/ 07 апреля 2019

Я понял это после 2 дней блокады!

Оба входных слоя не должны быть изменены, когда они определены.Изменение формы может быть продолжено на следующем шаге, входные слои должны быть независимо объявлены.

следующий фиксированный код: 

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)
)

, поэтому модель выглядит следующим образом 

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
_______________________________________________________________________________________________________________________________________________________________________________
...