ROG Kaggle

Kaggle-konkurransen er live!

Etter mandagens lunch & learn er vi klare til å gå i gang. Ettersom repoet for notebooken er privat, må deltakerne legge inn git- og kaggle handles for å få tilgang. Legg inn handles her.

• Lenke til konkurransen
• Lenke til notebook fra presentasjonen

URL til dagens meny i kantinen

Dagens meny kan leses i json her.

Datasett fra Stavanger kommune

Stavanger kommune legger ut åpne datasett her. Mye spennende data om folkehelse, inntekt, levekår, &c.

• Helseprofil
• Luftkvalitet
• Levekår, evt.
• Rutedata fra Kolumbus
• Demografi Stavanger

Brukerundersøkelse

Svar gjerne på Eriks brukerundersøkelse. Lenke til høyre, eller her.

Bildedatabaser

1. ImageNet: This is a large database of annotated images, and it's often used in image recognition and object detection tasks.
2. COCO (Common Objects in Context): This is a large-scale object detection, segmentation, and captioning dataset.
3. Open Images: It's a dataset from Google that is also used for object detection, visual relationship detection, and instance segmentation.
4. MNIST: This database contains a large set of handwritten digits that are commonly used for training various image processing systems.
5. Fashion MNIST: This is a dataset of Zalando's article images, with 28x28 grayscale images of 70,000 fashion products from 10 categories, and 7,000 images per category. The dataset is intended to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms, as it shares the same image size and structure of training and testing splits.
6. CelebA (CelebFaces Attributes Dataset): This is a large-scale face attributes dataset with more than 200,000 celebrity images, each with 40 attribute labels.