October 2018
Intermediate to advanced
246 pages
6h 26m
English
A VGG network can detect 1,000 objects inside a given input image. This takes image inputs of 224 * 244 * 3 in size (the number 3 represents RGB values). This is built using convolutional layers of 3 x 3 in size with a total of 16 layers. It also provides a Top-1 accuracy of 70.5% and a Top-5 accuracy of 90%.
Read now
Unlock full access