GoogLeNet
Implementation of GoogLeNet image classification network based on TensorFlow 2.0.
The neural network architecture proposed by Szegedy et al. exploits the current hardware’s computing power on dense matrices. As a result, the network can be wider and deeper while in the meantime consumes a similar amount of computing power as former networks.
[1] Szegedy, Christian, et al. “Going Deeper with Convolutions.” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, doi:10.1109/cvpr.2015.7298594.