1: Faster-rcnn代码
2:把实验数据跑完
-
if name == 'main' 如何正确理解?
http://blog.konghy.cn/2017/04/24/python-entry-program/
1.运行read_data.py 分别修改param为oxford和paris
create the lists of query and database images
-
在/data/imagelists中分别保存文件
- oxford
Saving text file: data/imagelists/oxford.txt
Saving text file: data/imagelists/query_oxford.txt
- paris
Saving text file: data/imagelists/paris.txt
Saving text file: data/imagelists/query_paris.txt
Filtering Stag. The Image-wise pooling (IPA) strategy is used to build image descriptors for both query and database images. At test time, the descriptor of the query image is compared to all the elements in the database, which are then ranked based on the cosine similarity. At this stage, the whole image is considered as the query.
- 先提取所有图片的特征以及数据库里面的特征,再把图片特征与数据库中的特征进行对比,用cosine大小来进行比较,形成第一步的query。
- 这一步使用的是图像的特征(IPA)与图像的区域特征(RPA)无关。
- 提取特征features.py,第一步比较ranking.py
2.运行features.py
extract Fast R-CNN features for all images in a dataset and store them to disk
先提取paris的参数,fast-rcnn里面的输入图片的参数设置为500.
结束时候的截图:
一开始的截图:
开始提取Oxford的特征:
生成的特征保存在data/features里面:
3.运行ranker.py
generate and store the rankings for the queries of the chosen dataset
先排Oxford的:
排Paris的:
结果保存在data/ranking里面:
Spatial Reranking. After the Filtering Stage, the top N elements are locally analyzed and reranked.
再次排列:
4.运行rerank.py文件
Rerank based on region features
先rerank Oxford数据集
再rerank Paris数据集
生成文件存在data/reranking里面
Query Expasion (QE). The image descriptors of the top
M elements of the ranking are averaged together with the
query descriptor to perform a new search。
ranking 里面的top5平均后进行一个新的search