Ashish Patel 🇮🇳’s Post

Day-49 Computer Vision Learning FBNet — FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search (Image Classification) by by University of California, Berkeley, Princeton University, and Facebook Inc Follow me for similar post : 🇮🇳 Ashish Patel Interesting Facts : 🔸 It is published in 2019 #CVPR, which has already got over 399 citations. 🔸 Outperforms DARTS, MnasNet, PNASNet, NASNet, ShuffleNet V2, MobileNetV2 & CondenseNet ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eVAFpEW official Code : https://bit.ly/3ub9JGT tensorflow: https://bit.ly/3pw57I3 pytorch: https://bit.ly/3avW3ib keras: https://bit.ly/3pw57I3 ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 A differentiable neural architecture search (DNAS) framework that uses gradient-based methods to optimize ConvNet architectures. 🔸 FBNets (Facebook-Berkeley-Nets), a family of models discovered by DNAS outperforms SOTA approaches. #computervision #artificialintelligence #technology