Uploading the files for a video cation generator based on cooking #115
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Related Issue
Info about the related issue
GSSOC Participant
Contributor
Closes: #6
Describe the changes you've made
It is Deep learning based Video caption generator especially for cooking videos. The algorithms used here are CNN-RNN model where LSTM(encoder-decoder) is used to predict the captions. Also a Nutrition API is included to get the nutritional information of the ingredients used.
Type of change
What sort of change have you made:
This project is done with specialization on cooking videos by taking only the videos based on cooking of the 1400 plus videos and trained to find the ingredients used, what the person is doing.
Steps Done
Feature Extraction
Preprocessing of Captions
LSTM for sequence generation
Model Building
Generating Caption using Greedy search
Libraries Used
opencv
pillow
keras
fpdf
py_edamam
joblif
anaconda
How Has This Been Tested?
Different algorithms has been tested over the training dataset and validated the prediction over the testing dataset. The most accurate algorithms among CNN,-RNN model with Greedy search for prediction instead of beam search as it has slow processing time. This gives an accuracy of 0.87 as BLEU score.
Checklist:
Screenshots
Updated Screenshot
![image](https://private-user-images.githubusercontent.com/68893681/244925041-4cc8a99e-8860-461d-ade4-16578f672717.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MjAzOTYxMzEsIm5iZiI6MTcyMDM5NTgzMSwicGF0aCI6Ii82ODg5MzY4MS8yNDQ5MjUwNDEtNGNjOGE5OWUtODg2MC00NjFkLWFkZTQtMTY1NzhmNjcyNzE3LnBuZz9YLUFtei1BbGdvcml0aG09QVdTNC1ITUFDLVNIQTI1NiZYLUFtei1DcmVkZW50aWFsPUFLSUFWQ09EWUxTQTUzUFFLNFpBJTJGMjAyNDA3MDclMkZ1cy1lYXN0LTElMkZzMyUyRmF3czRfcmVxdWVzdCZYLUFtei1EYXRlPTIwMjQwNzA3VDIzNDM1MVomWC1BbXotRXhwaXJlcz0zMDAmWC1BbXotU2lnbmF0dXJlPWY4YmJiNDZhZTIwOWE1YWRmOGRkNjNhOGZmNGNlZDMwM2ZlMWZjMDg4ZTg4ODBmYWQ3MTI0NmJhODc1NzVjMDImWC1BbXotU2lnbmVkSGVhZGVycz1ob3N0JmFjdG9yX2lkPTAma2V5X2lkPTAmcmVwb19pZD0wIn0.C0O7AgsM4T-uIk7JuNOGXblaznOBNkOGqk6PAj-c4yM)
README file is added