TypeError: 'int' object is not iterable when using model.fit()

Question

I tried to fit my model, but encountered 'type error'. This code was written almost the same as described in a kaggle source code example for CNN.

https://www.kaggle.com/kanncaa1/convolutional-neural-network-cnn-tutorial/notebook

However, continuously the type error occurs. I changed model.fit_generator to model. fit model. fit because the function is updated from the new version of tensorflow. I guessed shape[0] could make this int-relevant issue. Could anyone help to point out the wrong type in the code below?

# model fitting
# from tensorflow 2.1.0
history = model.fit(datagen.flow(train_x, train_y, batch_size = batch_size),
                          epochs = epochs,
                          validation_data = (valid_x, valid_y),
                          steps_per_epoch = train_x.shape[0] // batch_size)

Answer 1

Possible Solutions:

run print(x_train.shape) , and make sure all the values except the first dimension match the input_shape that you specified during the model definition. If you ported the code from the kaggle kernel then I assume your model was defined as:

model.add(Conv2D(filters = 8, kernel_size = (5,5),padding = 'Same', 
                 activation ='relu', input_shape = (28,28,1)))

Make Sure that x_train.shape is in accordance with the specified input_shape .