"unknown node" error in Keras convolutional neural network - image-processing

Question

I have the following (2D) convolutional neural network in Keras for image classification with binary labels:
model = keras.Sequential()
model.add(Conv2D(32, kernel_size=5, activation='relu', input_shape=(128, 128, 1)))
model.add(MaxPooling2D(pool_size=2))
model.add(Conv2D(64, kernel_size=5, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Flatten())
model.add(Dense(1024, activation="relu"))
model.add(Dense(2, activation="softmax"))
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
To train it, I have a lot of (.jpeg) image files, but too many to load all at once. Hence I use the following generator (and preprocessing):
def load_preprocess(path):
img = img_to_array(load_img(path, target_size=(128, 128)))
output = rgb_to_grayscale(img)
output = tf.reshape(output, (-1,128, 128, 1))
return output
def image_generator(paths, labels, batch_size=32):
while True:
for i in range(0, len(paths), batch_size):
images = [load_preprocess(path) for path in paths[i:i+batch_size]]
target = labels[i:i+batch_size]
yield(images, target)
I tried training the network using
model.fit_generator(image_generator(train_paths, train_labels), steps_per_epoch=int(np.ceil(len(train_paths)/32)), epochs=1)
Here train_paths is a list of paths and train_labels is a binary numpy array with two columns.
However, this gives me the following error:
InvalidArgumentError: Requested tensor connection from unknown node: "conv2d_input:0".
What causes this error and how do I solve it? I tried googling it, but I found no hits at all.

Answer 1

I found the error: the images are tensors and should be converted to arrays. I do this as follows:
def image_generator(paths, labels, batch_size=32):
sess = tf.Session()
while True:
for i in range(0, len(paths), batch_size):
with sess.as_default():
images = [load_preprocess(path).eval() for path in paths[i:i+batch_size]]
target = labels[i:i+batch_size]
yield(np.array(images), target)