The final project of the course Python for Data Science, on the Web framework - Django.
With this application, you will be able to make a prediction of the uploaded picture using the trained cifar10 and cifar100 datasets, as well as the integrated chatGPT will help you find answers to questions about neural networks from the book "Deep Learning in Python" by FRANÇOIS CHOLLET.
Image-Recognizer - it performs the following functions:
- cifar10 - Identifies images in pictures and makes predictions for them based on the 10 image classes that have been trained.
- cifar100 - Identifies images in pictures and makes predictions for them based on the 100 image classes that have been trained.
- chatGPT - will help you find answers to questions about neural networks from the book "Deep Learning in Python" by FRANÇOIS CHOLLET. The author hopes that this book will be useful to you and help you start creating intelligent applications and solving problems that are important to you.
Project is mainly based on:
- Web framework: Django
- Frontend: HTML/CSS, Tailwind.css, Node.js
- Backend: python, JavaScript, Google Colab, Anaconda, Tensorflow, Keras, Numpy
-
The first thing to do is download Node.js and install it:
-
The second thing to do is to clone the repository:
$ git clone [email protected]:maracasabat/Image-Recognizer-WEB.git
- Activate virtual environment and install dependencies:
$ pipenv shell
(env)$ pipenv install
- Once
pipenv
has finished downloading the dependencies:
(env)$ cd recognizer/frontend/static_src/
(env)$ npm i
- Create .env file in project root and fill in the file like this example:
SECRET_KEY=secret_key
ALLOWED_HOSTS=*
POSTGRES_DB_NAME=postgres
POSTGRES_USER=postgres
POSTGRES_PASSWORD=password
POSTGRES_HOST=db
POSTGRES_PORT=5432
OPENAI_API_KEY=OPENAI_API_KEY
- If you want to use Cloudinary add next steps:
CLOUD_NAME=cloudinary_NAME
API_KEY=cloudinary_KEY
API_SECRET=cloudinary_SECRET
- Or you can choose local storage on file settings.py
if you use Windows choose next option on file settings.py:
NPM_BIN_PATH = r"C:\Program Files\nodejs\npm.cmd" # Windows
else:
NPM_BIN_PATH = '/usr/local/bin/npm' # MacOS
First terminal:
(env)$ cd recognizer
(env)$ python manage.py migrate
(env)$ python manage.py tailwind build
(env)$ python manage.py tailwind start
Second terminal:
(env)$ cd recognizer
(env)$ python manage.py runserver
-
And navigate to `http://127.0.0.1:8000/.
-
Links to the models: