Whenever an image appears in front of us our brain is capable of annotating or labeling it. But, what about computers? How can a machine process an image and label it with a highly relevant and accurate caption?

describe what can people use it for, or how it makes existing tasks easier/safer e.t.c (markdown supported)

The problem it solves

Collection of dataset of images was a much big problem.

tell us about any specific bug or hurdle you ran into while building this project. how did you get over it? (markdown supported)

Challenges we ran into

Reckon 4.0

TensorFlow

Keras

Python

LSTM

Convolutional Neural Networks(CNN)

Caption Generator

In This project  we build a deep learning model with the help of CNN and LSTM. We used a very small dataset of 8000 images to train our model,

Software

Bhole Chature

Caption Generator

build a relevant caption generator for an image

Caption Generator

build a relevant caption generator for an image

The problem Caption Generator solves

Challenges we ran into

Software

Discussion

Builders also viewed