Ashish Patel 🇮🇳’s Post

Day-65 Computer Vision Learning MegDet — A Large Mini-Batch Object Detector, 1st Place of COCO 2017 Detection Challenge (Object Detection) Follow me for similar post : 🇮🇳 Ashish Patel Interesting Facts : 🔸 It is published in 2018 CVPR, which has already got over 191 citations. 🔸 Large Mini-Batch Size of 256 With Warmup Learning Rate Policy and Cross-GPU Batch Normalization, the training time is reduced From 33 hrs To 4 hrs ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eRZs2jt Official Code : https://bit.ly/3cbSzB7 pytorch : https://bit.ly/3emNaJQ ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 a Large Mini-Batch Object Detector (MegDet) is proposed to enable the training with a large mini-batch size up to 256 so that we can effectively utilize at most 128 GPUs to significantly shorten the training time. 🔸 A warmup learning rate policy and Cross-GPU Batch Normalization are suggested, which together allow us to successfully train a large mini-batch detector in much less time (e.g., from 33 hours to 4 hours), and achieve even better accuracy. #computervision #artificialintelligence #technology