Ashish Patel 🇮🇳’s Post

Day-34 Computer Vision Learning PolyNet by CUHK and SenseTime 商汤科技 Follow me for similar post : 🇮🇳 Ashish Patel 🇮🇳 Interesting Facts : 🔸 It is published in 2017 #CVPR , which has already got over 152 citations 🔸 A Very Deep PolyNet is composed based on the module. 🔸 Compared to Inception-ResNet-v2, PolyNet reduces the Top-5 validation error on single crops from 4.9% to 4.25%, and that on multi-crops from 3.7% to 3.45%. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/gjyCkMd Pytorch : https://bit.ly/3pPT89m Tensorflow : https://bit.ly/3jb4WAp ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Any second-order PolyInception module is better than Inception module. 🔸 Very Deep Inception-ResNet: Inception-ResNet-v2 with IR 20–56–20. 19.10% Top-1 Error and 4.48% Top-5 Error are obtained. 🔸 Verp Deep PolyNet (10–20–10 mix): 18.71% Top-1 Error and 4.25% Top-5 Error are obtained. #computervision #data #artificialintelligence