Image-to-text model.
This python Deeplearning model uses CNN-LSTM to create captions for images.
The database used was the Flicker8k_Dataset (https://github.com/jbrownlee/Datasets/releases/download/Flickr8k/Flickr8k_Dataset.zip) database and Flickr_8k_text (https://github.com/jbrownlee/Datasets/releases/download/Flickr8k/Flickr8k_text.zip)
The model was trained on an Intel Core i5 processor and due to computational reasons the model did not achieve satisfactory results. I recommend using a GPU in addition to increasing the training time to achieve good results.