October 2018
Intermediate to advanced
472 pages
10h 57m
English
For this implementation, we will be using the COCO dataset. This is a great resource dataset for training YOLOv2 to detect, segment, and caption images on a large scale. Download the dataset from http://cocodataset.org and run the following command in the terminal:
wget http://images.cocodataset.org/zips/train2014.zip
wget http://images.cocodataset.org/zips/val2014.zip
wget http://images.cocodataset.org/annotations/annotations_trainval2014.zip
Now, let's convert the annotations in the COCO format to VOC format:
pip install baker
Read now
Unlock full access