Skip to content

Making use of (Language model + Image model) to generate captions on flickr images. CNN + LSTM + Transfer learning

Notifications You must be signed in to change notification settings

Abbasidi/Image-Captioning-System-Using-Deep-Learning

Repository files navigation

Image-Captioning-System-Using-Deep-Learning

Making use of (Language model + Image model) to generate captions on flikr8k images. CNN + LSTM + Transfer learning

What Is Image Captioning Using Deep Learning?

Image Captioning Using Deep Learning Deep Learning Application. In Which we have to pass the image to the model and the model does some processing and generating captions or descriptions as per its training. This prediction is sometimes not that much accurate and generates some meaningless sentences. We need very high computational power and a very huge dataset for better results.

Get in touch with team -> [Ghulam Abbas] (malikghulamabbas894@gmail.com)

How To Run This Project?

  1. Download and extract Flickr8k_Dataset.zip and Flickr8k_text.zip

  2. Now, create a folder named 'ML' in root directory of your Google Drive.

  3. Then upload extracted version of Flickr8k_Dataset and Flickr8k_text into the ML folder. This may take times depending on your IP provider.

  4. Also upload the testing_caption_generator.py into ML folder.

  5. Now create a notebook in Google Colab by Image_Captioning_Using_Deep_Learning name, and copy paste Shells from ImageCaption.ipynb

  6. Then Run all the shells.

Do not use it for Commercially.

About

Making use of (Language model + Image model) to generate captions on flickr images. CNN + LSTM + Transfer learning

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published