The VGG is the convolution neural network for object recognition developed and trained by Oxford’s Visual Geometry Group. And what is VGG-19? This is the neural network with 19 layers deep, and this CNN can classify images into 1000 object categories.

Wojciech Rosinski performed the training time comparison for 3 popular frameworks: *Tensorflow 1.4.0*, *Keras 2.1.1*, *Pytorch 0.2.0+f964105.*

Training is performed for 10 epochs, each model is trained with Adam (adaptive learning rate optimization algorithm, first published in 2014) and SGD (stochastic gradient descent) , with batch size = 4 and batch size = 16, this results in 4 runs per model per framework. Pytorch wins, at least, on VGG-19 network tests: