A health/food monitoring application. Many times things like nutritional information or something like that are ignored. These can indirectly cause other issues and build up chronically. We hope to solve this problem and help people stay fit!It also reminds you to take medicines and do Yoga!
Python, Deep Neural Networks, HTML, CSS, Django,Flask,Javascript
- The colab file: https://colab.research.google.com/drive/1IEv2L1moJLGrZIKeHwlWxkPBiU9kOG4c#scrollTo=GfCsbyialA8N
- google drive folder: https://drive.google.com/drive/folders/1Fwp-zK_7-XH320W-6YHwvVqKjLGpbG6D?usp=sharing
Posenet, Tensorflow, pyttsx3, schedule, random, time, getpass
Installations needed:
1.pyttsx3: This project is written in Python 3.8.3 using Pyttsx3 (text-to-speech conversion library in Python. Unlike alternative libraries, it works offline, and is compatible with both Python 2 and 3.
pip install pyttsx3
2.schedule: Python job scheduling for humans. Run Python functions (or any other callable) periodically using a friendly syntax.
pip install schedule
- getpass: getpass() prompts the user for a password without echoing. The getpass module provides a secure way to handle the password prompts where programs interact with the users via the terminal
4.Tensorflow: TensorFlow is a free and open-source software library for machine learning. It can be used across a range of tasks but has a particular focus on training and inference of deep neural networks. Tensorflow is a symbolic math library based on dataflow and differentiable programming.
pip install Tensorflow
- Keras:
- Django:
- Posenet: PoseNet can be used to estimate either a single pose or multiple poses, meaning there is a version of the algorithm that can detect only one person in an image/video and one version that can detect multiple persons in an image/video.
(Requirements file will be added later)
-
Run the code in the .ipynb file on colab
-
Click the first link("public_url") in the scond last cell which looks something like this:
<NgrokTunnel: "http://a79b8420f21b.ngrok.io" -> "http://localhost:80">
- We haven't actually deployed the django part("Wellexa-Project" folder in this repo), so you would have to run it on local host to check it
None
- Improved colab link: https://colab.research.google.com/drive/1v3IQlu1f-pleIZkoOTLAhxNmj_dwndmg?usp=sharing
- Sample image URLs to try:
(currently image URLs work and they need to be of jpeg/png/jpeg format)
https://image.shutterstock.com/image-photo/masala-dosa-indian-savory-crepes-600w-783911236.jpg
https://as1.ftcdn.net/jpg/02/21/25/16/1000_F_221251677_H4e9ADfkdV8kyLRLbHrU9oxzy4DDaxth.jpg
- Sample image URLs to try:
(currently image URLs work and they need to be of jpeg/png/jpeg format)
https://image.shutterstock.com/image-photo/masala-dosa-indian-savory-crepes-600w-783911236.jpg
- Fixed Tensorflow errors, To test the app,
- Clone the repo
- Copy and paste "best_model.h5" from the google drive folder link mentioned above to the "Wellexa-Project" folder
- Run the server locally by entering the command
python manage.py runserver
in the Wellexa-Project directory - Enter the local address to open the home/food monitor page
- Upload the file