no code implementations • 16 Jan 2017 • Tapabrata Ghosh
In recent times, the use of separable convolutions in deep convolutional neural network architectures has been explored.
no code implementations • 9 Jan 2017 • Tapabrata Ghosh
We present QuickNet, a fast and accurate network architecture that is both faster and significantly more accurate than other fast deep architectures like SqueezeNet.