Day-43 Computer Vision Learning 𝗦𝗵𝘂𝗳𝗳𝗹𝗲𝗡𝗲𝘁 𝗩2 — Practical Guidelines for Efficient CNN Architecture Design(Image Classification) by MEGVII旷视 Inc (Face++), and Tsinghua University Follow me for similar post : 🇮🇳 Ashish Patel Interesting Facts : 🔸 It is published in 2018 #ECCV, which has already got over 1026 citations. 🔸 Outperforms MobileNetV1, MobileNetV2, ShuffleNet V1, DenseNet, CondenseNet, Xception, IGCV2, IGCV3, NASNet-A, PNASNet-5, SENet & ResNet ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/e_PTYdj official Code : https://bit.ly/3tMQ7bX tensorflow: https://bit.ly/3adk2T2 pytorch: https://bit.ly/3qgo0zZ keras: https://bit.ly/2ZboiMA ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Practical guidelines are suggested for efficient network design using MAC and experimental observations using GPU/ARM. 🔸 ShuffleNet V2 is proposed according to the practical guidelines, which obtains high accuracy with also high speed. #computervision #artificialintelligence #datascience
For previous post visit this github : https://github.com/ashishpatel26/365-Days-Computer-Vision-Learning-Linkedin-Post #deeplearning #india #technology
Thank you for sharing