2 code implementations • 19 Mar 2019 • Sambhav R. Jain, Albert Gural, Michael Wu, Chris H. Dick
We propose a method of training quantization thresholds (TQT) for uniform symmetric quantizers using standard backpropagation and gradient descent.
1 code implementation • 27 Jun 2017 • Sambhav R. Jain, Kye Okabe
After 15 fully convolutional stages followed by a score comparator, the network outputs 8 layout layers (corresponding to 4 route layers, 3 via layers and an identity-mapped pin layer) which are then decoded to obtain the routed layouts.