February 2019
Beginner to intermediate
308 pages
7h 42m
English
VGG16 was developed by Oxford's Visual Geometry Group (VGG) and it was considered to be a very important neural network. VGG16 was one of the first CNNs to deviate from large filter sizes, instead using a convolution filter size of 3 x 3.
VGG16 finished second in the image recognition task in the ILSVRC in 2014. A downside to VGG16 is that there are many more parameters to be trained, leading to a significant training time.
Read now
Unlock full access