GitHub - fede-vaccaro/image-retrieval-web-engine: A simple content-based image retrieval engine powered by CNN. Backend based on Django and Keras/Tensorflow. Frontend in AngularJS.

fede-vaccaro / image-retrieval-web-engine Public

Notifications You must be signed in to change notification settings
Fork 1
Star 4

A simple content-based image retrieval engine powered by CNN. Backend based on Django and Keras/Tensorflow. Frontend in AngularJS.

4 stars 1 fork Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 53 Commits
api		api
frontend		frontend
image_prova		image_prova
images		images
yael		yael
Readme.txt		Readme.txt
image_patches_mpipe.py		image_patches_mpipe.py
image_patches_serial.py		image_patches_serial.py
manage.py		manage.py
populate_db.py		populate_db.py
train_from_directory.py		train_from_directory.py
yael_script.py		yael_script.py
yael_script_window.py		yael_script_window.py
yael_wrapper.py		yael_wrapper.py

Repository files navigation

Needed package:

numpy;
tensorflow(<1.5);
keras; 
django;
django_restframework;
pillow;
h5py;

copy "populate_db.py" to ~/lib/site-packages/django/core/managament/commands/

I suggest to create a virtualenv.
1) python manage.py makemigrations (this is supposed to doesn't be needed but do it the same) 
2) python manage.py migrate (to create the tables)

after copy the populate_db file where specified above, put your image dataset (only .jpg supported for now) in image-retrieval-web-engine/img/ 

3) python manage.py populate_db

Try it in 127.0.0.1:8000 by 

4) python manage.py runserver