![]() Fast R-CNN is implemented in Python and C++ (using Caffe) and is available under the open-source MIT License at https: ///rbgirshick/fast-rcnn. Compared to SPPnet, Fast R-CNN trains VGG16 3× faster, tests 10× faster, and is more accurate. Fast R-CNN trains the very deep VGG16 network 9× faster than R-CNN, is 213× faster at test-time, and achieves a higher mAP on PASCAL VOC 2012. Compared to previous work, Fast R-CNN employs several innovations to improve training and testing speed while also increasing detection accuracy. Fast R-CNN builds on previous work to efficiently classify object proposals using deep convolutional networks. ![]() 目标检测经典论文翻译汇总: 翻译pdf文件下载: 此版为纯中文版,中英文对照版请稳步: Fast R-CNN Ross Girshick Microsoft Research(微软研究院) paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection.
0 Comments
Leave a Reply. |