Closed Lotuslisa closed 9 years ago
Beside trying the Overfeat, I will use the faster RCNN to extract features. I will implement fast RCNN on the cluster instead my own laptop.
Faster-Rcnn is an improvement over Fast-rcnn. And it works. For his reason no work on Fast-rcnn will be done at this time
Except for the Overfeat, I will implement Fast RCNN for detection and feature extraction. Then we can compare the performence of these three models and see which one is better for our problem.
Fast R-CNN is a fast framework for object detection with deep ConvNets. Fast R-CNN trains state-of-the-art models, like VGG16, 9x faster than traditional R-CNN and 3x faster than SPPnet, runs 200x faster than R-CNN and 10x faster than SPPnet at test-time, has a significantly higher mAP on PASCAL VOC than both R-CNN and SPPnet, and is written in Python and C++/Caffe.