We’ve used deep learning to build an object detector on the PASCAL VOC dataset. The detector is trained to recognise 20 different types of objects:

  • Person: person
  • Animal: bird, cat, cow, dog, horse, sheep
  • Vehicle: aeroplane, bicycle, boat, bus, car, motorbike, train
  • Indoor: bottle, chair, dining table, potted plant, sofa, tv/monitor

If you provide an image containing some of these objects, the network should localise them!

Note: Please keep images below 2 MB in size.