ValueError: No gradients provided for any variable——Keras/Tensorflow

I'm trying to implementing a Keras Model for an image captioning network, and I define my model like so:

import os
from keras.applications.vgg16 import VGG16
import numpy as np 
from numpy import array, argmax, random, take
from pickle import dump
from pickle import load
import string
from keras.applications.imagenet_utils import preprocess_input  
from keras.models import Model
from keras.preprocessing.image import load_img
from keras.preprocessing.image import img_to_array
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
from keras.utils import to_categorical

import tensorflow as tf

from keras.utils import plot_model
from keras.layers import Input
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers import Embedding
from keras.layers import Dropout
from keras.layers.merge import add
from keras.callbacks import ModelCheckpoint
from keras.losses import categorical_crossentropy
import matplotlib.pyplot as plt
%matplotlib inline
from nltk.translate.bleu_score import corpus_bleu


def create_sequences(tokenizer, max_length, desc_list, photo):
    X1, X2, y = list(), list(), list()
    for desc in desc_list:       
        seq = tokenizer.texts_to_sequences([desc])[0]
        print(len(seq))
        for i in range(1, len(seq)):
            in_seq, out_seq = seq[:i], seq[i]
            in_seq = pad_sequences([in_seq], maxlen=max_length)[0]     
            out_seq = to_categorical([out_seq], num_classes=vocab_size)[0]
            X1.append(photo)  
            X2.append(in_seq)
            y.append(out_seq)
    return array(X1), array(X2), array(y)

def define_model(vocab_size, max_length):
    inputs1 = Input(shape=(4096,))
    fe1 = Dropout(0.5)(inputs1)
    fe2 = Dense(256, activation='relu')(fe1)
    inputs2 = Input(shape=(max_length,))
    se1 = Embedding(vocab_size, 256, mask_zero=True)(inputs2)
    se2 = Dropout(0.5)(se1)
    se3 = LSTM(256)(se2)
    decoder1 = add([fe2, se3])
    decoder2 = Dense(256, activation='relu')(decoder1)
    outputs = Dense(vocab_size, activation='softmax')(decoder2)
    model = Model(inputs=[inputs1, inputs2], outputs=outputs)
    model.compile(loss='categorical_crossentropy', optimizer='adam')
    print(model.summary())
    return model

def data_generator(descriptions, photos, tokenizer, max_length):
    while 1:
        for key, desc_list in descriptions.items():
            photo = photos[key]
            print(photo.shape)
            print(len(desc_list))         
            in_img, in_seq, out_word = create_sequences(tokenizer, max_length, desc_list, photo)
            yield [[in_img, in_seq], out_word]

then running the fit method:

filepath = 'model-ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}.h5'
checkpoint = ModelCheckpoint(filepath, monitor='val_loss', verbose=1, save_best_only=True, mode='min')

model = define_model(vocab_size, max_length)
steps = len(train_descriptions)
generator = data_generator(train_descriptions, train_features, tokenizer, max_length)
val_generator=data_generator(test_descriptions, test_features, tokenizer, max_length)
model.fit(generator, epochs=20, steps_per_epoch=steps, verbose=1,callbacks=[checkpoint],validation_data=val_generator,validation_steps=1)

I get the error:

ValueError: No gradients provided for any variable: ['embedding_1/embeddings:0', 'dense_3/kernel:0', 'dense_3/bias:0', 'lstm_1/lstm_cell_1/kernel:0', 'lstm_1/lstm_cell_1/recurrent_kernel:0', 'lstm_1/lstm_cell_1/bias:0', 'dense_4/kernel:0', 'dense_4/bias:0', 'dense_5/kernel:0', 'dense_5/bias:0'].

And I try the fit method without generator, getting the new error:

ValueError: Input 0 of layer dense_24 is incompatible with the layer: expected axis -1 of input shape to have value 4096 but received input with shape [None, 1]

Can anyone help me? I don't know where is the error because i have never seen it before I have been checking similar posts in SO but none of the solutions there has worked for me

Thanks in advance!