Custom Implementation of Non-Deep Networks

Nov 05, 2021 1 min read

ParNet

Custom Implementation of Non-deep Networks

arXiv:2110.07641
Ankit Goyal, Alexey Bochkovskiy, Jia Deng, Vladlen Koltun

Official Repository https://github.com/imankgoyal/NonDeepNetworks

Overview: Depth is the hallmark of DNNs. But more depth means more sequential computation and higher latency. This begs the question — is it possible to build high-performing “non-deep” neural networks? We show that it is. We show, for the first time, that a network with a depth of just 12 can achieve top-1 accuracy over 80% on ImageNet, 96% on CIFAR10, and 81% on CIFAR100. We also show that a network with a low-depth (12) backbone can achieve an AP of 48% on MS-COCO.

If there is any issue in the code, please feel free to update.

GitHub

View Github

Deep Learning Network

John was the first writer to have joined pythonawesome.com. He has since then inculcated very effective writing and reviewing culture at pythonawesome which rivals have found impossible to imitate.