https://github.com/aryanjain28/image-caption-generator

Fused RNN and CNN to predict image activity by amalgamating Xception model output and text input for enhanced accuracy.
https://github.com/aryanjain28/image-caption-generator

cnn computer-vision data-science machine-learning neural-network python rnn tensorflow

Last synced: about 2 months ago
JSON representation

Fused RNN and CNN to predict image activity by amalgamating Xception model output and text input for enhanced accuracy.

Host: GitHub
URL: https://github.com/aryanjain28/image-caption-generator
Owner: aryanjain28
Created: 2020-07-02T06:28:35.000Z (about 6 years ago)
Default Branch: master
Last Pushed: 2020-07-02T12:33:56.000Z (about 6 years ago)
Last Synced: 2025-05-31T14:17:49.938Z (about 1 year ago)
Topics: cnn, computer-vision, data-science, machine-learning, neural-network, python, rnn, tensorflow
Language: Jupyter Notebook
Homepage:
Size: 2.27 MB
Stars: 0
Watchers: 1
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

# Image Caption Generator

Trained a model by merging RNN and CNN to generate the activity occuring on the image. The model takes pre-trained output from another model, Xception, as image's input and takes another input from text and merges them and generates predictions.

# BLEU scores

Below is a chart that I prepared for the BLEU score of my VGG16 and Xception model.
The higher the BLEU score, the higher the accuracy of Model.
You can see the Xception Model-4 has the highest score, and that is the model used in this project.

# Screenshots

Below are some screenshots, half of them are from training set while others are randomly picked from internet.
As observed below some results are exceptionally good, while some are too bad.