I am attempting to build a simple CNN that takes four 100x100 grayscale images as inputs and tells me which one contains a circle. I am having trouble with the interaction between my generator and my CNN inputs, my inputs expect an array of dimension 4 but get an array of shape (100, 100, 1) as expected.

multi_image.py

import numpy as np
import os
from keras.models import Model
from keras.layers import Input
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense
from keras.layers.merge import concatenate

input_1 = Input(shape = (100, 100, 1), dtype = 'float32')
input_2 = Input(shape = (100, 100, 1), dtype = 'float32')
input_3 = Input(shape = (100, 100, 1), dtype = 'float32')
input_4 = Input(shape = (100, 100, 1), dtype = 'float32')

output_1 = Conv2D(32, (3, 3), activation = 'relu')(input_1)
output_1 = MaxPooling2D(pool_size = (2, 2))(output_1)
output_1 = Conv2D(32, (3, 3), activation = 'relu')(output_1)
output_1 = MaxPooling2D(pool_size = (2, 2))(output_1)
output_1 = Flatten()(output_1)

output_2 = Conv2D(32, (3, 3), activation = 'relu')(input_2)
output_2 = MaxPooling2D(pool_size = (2, 2))(output_2)
output_2 = Conv2D(32, (3, 3), activation = 'relu')(output_2)
output_2 = MaxPooling2D(pool_size = (2, 2))(output_2)
output_2 = Flatten()(output_2)

output_3 = Conv2D(32, (3, 3), activation = 'relu')(input_3)
output_3 = MaxPooling2D(pool_size = (2, 2))(output_3)
output_3 = Conv2D(32, (3, 3), activation = 'relu')(output_3)
output_3 = MaxPooling2D(pool_size = (2, 2))(output_3)
output_3 = Flatten()(output_3)

output_4 = Conv2D(32, (3, 3), activation = 'relu')(input_4)
output_4 = MaxPooling2D(pool_size = (2, 2))(output_4)
output_4 = Conv2D(32, (3, 3), activation = 'relu')(output_4)
output_4 = MaxPooling2D(pool_size = (2, 2))(output_4)
output_4 = Flatten()(output_4)

inputs = [input_1, input_2, input_3, input_4]
outputs = [output_1, output_2, output_3, output_4]

combine = concatenate(outputs)

output = Dense(64, activation = 'relu')(combine)
output = Dense(4, activation = 'sigmoid')(output)

model = Model(inputs = inputs, outputs = [output])

model.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics = ['accuracy'])

from keras.preprocessing.image import ImageDataGenerator, img_to_array, load_img

def input_generator(folder, directories):
       
    Streams = []
    for i in range(len(directories)):
        Streams.append(os.listdir(folder + "/" + directories[i]))
        for j in range(len(Streams[i])):
            Streams[i][j] = "Stream" + str(i + 1) + "/" + Streams[i][j]   
        Streams[i].sort()
    
    
    length = len(Streams[0])
    index = 0
    while True:
        X = []
        y = np.zeros(4)
        for Stream in Streams:
            image = load_img(folder + '/' + Stream[index], grayscale = True)
            array = img_to_array(image)
            X.append(array)
        y[int(Stream[index][15]) - 1] = 1
        index += 1
        index = index % length
        yield X, y

# Number of epochs
nb_epoch = 100

model.fit_generator(generator = input_generator("multi_shape_database", ['Stream1', 'Stream2', 'Stream3', 'Stream4']), 
                                                    steps_per_epoch = 12000 / 32,
                                                    epochs = nb_epoch)