In this project, you will create a neural network architecture to automatically generate captions from images. Project Overview In this project, you will create a neural network architecture to automatically generate captions from images.
After using the Microsoft Common Objects in COntext (MS COCO) dataset to train your network, you will test your network on novel images!
Project Instructions The project is structured as a series of Jupyter notebooks that are designed to be completed in sequential order:
-
0_Dataset.ipynb
-
1_Preliminaries.ipynb
-
2_Training.ipynb
-
3_Inference.ipynb
Vocabulary file and pickle file to train all the captions model.py (RNN structure with ResNet)
You MUST enable GPU mode for this project
