0

short version:
what does the None in the Output Shape column of keras .summary() mean()?

long version: Here's simple keras code for creating a NN. i'm interested in how to interpret the text from the .summary() call:

model0 = Sequential()

model0.add(Flatten(input_shape=(1, img_rows, img_cols)))
model0.add(Dense(nb_classes))
model0.add(Activation('softmax'))
print(model0.summary())

In the following output of the program

Layer (type)         Output Shape   Param #     Connected to                     
=====================================================================
flatten_1 (Flatten)   (None, 784)     0           flatten_input_1[0][0]            
dense_1 (Dense)     (None, 10)       7850        flatten_1[0][0]                  
activation_1        (None, 10)          0           dense_1[0][0]                    
======================================================================
Total params: 7850

what does the what does the None in the Output Shape column of keras .summary() mean()?

Aviad Rozenhek
  • 2,130
  • 3
  • 19
  • 40

0 Answers0