TensTorrent。一家位于Toronto的start-up,研发专为深度学习和智能硬件而设计的高性能处理器,技术人员来自NVDIA和AMD。 Deep Learning Unit。深度学习单元。Fujitsu(富士通)最近高调宣布了自家的AI芯片,命名为DLU。名字虽然没什么创意,但是可以看到DLU已经被富士通标了“TM”,虽然TM也没啥用。在其公布的信息里可以看到,DL...
Computational Camera and Photography - Ramesh Raskar (MIT Media Lab) Computational Photography - Irfan Essa (Georgia Tech) Courses in Graphics - Stanford University Computational Photography - Rob Fergus (NYU) Introduction to Visual Computing - Kyros Kutulakos (University of Toronto) Computational Photogra...
The loss function was designed as a sum of two terms: binary cross-entropy and Dice coefficient-related loss of the three predicted masks [20,21,22]. We used the optimizer RMSprop (unpublished, adaptive learning rate method proposed by Geoff Hinton here http://www.cs.toronto.edu/tijmen/csc...
intro: a person detector on n fish-eye images of indoor scenes(NIPS 2018) arxiv:https://arxiv.org/abs/1805.08503 datasets:https://gitlab.com/omnidetector/omnidetector YOLOv3 YOLOv3: An Incremental Improvement arxiv:https://arxiv.org/abs/1804.02767 paper:https://pjreddie.com/media/files/pa...
https://www.cs.toronto.edu/~delve/data/boston/bostonDetail.html 地理数据集 Google-Landmarks-v2:用于地标识别和检索的数据集。该个数据集包含了来自世界各地的5百万张,包含20万多个地标的图片,这些图片由Wiki Commons社区提供和注释。 https://www.kaggle.com/xiuchengwang/python-dataset-download ...
This is a list of awesome articles about object detection. If you want to read the paper according to time, you can refer to Date. R-CNN Fast R-CNN Faster R-CNN Mask R-CNN Light-Head R-CNN Cascade R-CNN SPP-Net YOLO YOLOv2 ...