Dataset

Open Food Facts – World

A collaborative, free and open database of ingredients, nutrition facts and information on food products from around the world.

Source: openfoodfacts.org/

Open Food Facts

Faster R-CNN (object detection) implemented by Keras for custom data from Google’s Open Images…

The whole dataset of Open Images Dataset V4 which contains 600 classes is too large. So we extract 1,000 images for three classes, ‘Person’, ‘Mobile phone’ and ‘Car’ respectively.

Source: towardsdatascience.com/faster-r-cnn-object-detection-implemented-by-keras-for-custom-data-from-googles-open-images-125f62b9141a

Faster R-CNN (object detection) implemented by Keras for custom data from Google’s Open Images

Automate FloydHub with Celery

Ubidots is an Internet of Things (IoT) data analytics and visualization company. We transform sensor data into information that powers business decisions, and we’re using FloydHub to build and launch our latest feature – detecting anamolies from images captured by IoT devices. This way, the entire object detection pipeline is automated using celery and requires no manual intervention by our engineers.

Source: blog.floydhub.com/automate-floydhub-with-celery/

Automate FloydHub with Celery

On Building an Instagram Street Art Dataset and Detection Model

In this article, we will go over how to build a deep learning model using TensorFlow and Keras that accomplishes the task of generally detecting street art by using publicly available social media data on Instagram.

Source: blog.floydhub.com/instagram-street-art/

On Building an Instagram Street Art Dataset and Detection Model