Hugging Face's logo

keras-io
/
image-captioning

Image-to-Text
TF-Keras
generic
Model card Files Community
image-captioning / README.md
merve's picture
merve HF staff
Update README.md
d161bf2
preview code
|
raw
history blame contribute delete
1.71 kB
metadata
tags:
  - image-to-text
  - generic
library_name: generic
pipeline_tag: image-to-text
widget:
  - src: >-
      https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-1.jpg
    example_title: Kedis
  - src: >-
      https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-2.jpg
    example_title: Cat in a Crate
  - src: >-
      https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-3.jpg
    example_title: Two Cats Chilling
license: cc0-1.0

Tensorflow Keras Implementation of an Image Captioning Model with encoder-decoder network. 🌃🌅🎑

This repo contains the models and the notebook on Image captioning with visual attention.

Full credits to TensorFlow Team

Background Information

This notebook implements TensorFlow Keras implementation on Image captioning with visual attention. Given an image like the example below, your goal is to generate a caption such as "a surfer riding on a wave". image To accomplish this, you'll use an attention-based model, which enables us to see what parts of the image the model focuses on as it generates a caption. attention The model architecture is similar to Show, Attend and Tell: Neural Image Caption Generation with Visual Attention.

This notebook is an end-to-end example. When you run the notebook, it downloads the MS-COCO dataset, preprocesses and caches a subset of images using Inception V3, trains an encoder-decoder model, and generates captions on new images using the trained model.