willard-yuan / cnn-for-image-retrieval Goto Github PK

Hey, saw your repo and blog about visual search.
You might be interested in my project Deep Video Analytics.
Which implements full fledged visual search and data analytics engine.

https://github.com/AKSHAYUBHAT/DeepVideoAnalytics/

Hi, I think there is mistake in computing average precision as ap(i,1) = sum(precision)/queryClassNum. According to the formula, the denominator should be the non-zero items in precision vector rather than the number of retrieval categories, right?

tools/retrieval_virsulazation.m

% %for loop = 1:n
% % VecTemp = featNorm(loop, :);
% % score(loop) = QueryVec*VecTemp';
% %end

score = (QueryVec*featNorm')';

用了http://www.vlfeat.org/matconvnet/pretrained/下的vgg-m-1024模型提取特征,CPU差不多一秒钟5张,GPU(GTX970)快了不少一秒钟50张左右

hi, i am very interested in your work on image retrieval, and my question is how can i apply it to the video retrieval domains. there mainly two pints make me confused:
firstly, image retrieval take CNN as the feature extractor , and the CNN mainly trained with the classification loss on such cifar-10 or landmark dataset(Oxf5k), can it generalize to the actual video scenarios(usually are not landmark)? fine-tuning needed? and how?
secondly, how can i calculate the similarity between the query video and reference video, my method is dividing video into key frames and match the similar frames by extracting the frame features
can you give me some opinion. thanks!

你好，
我打开你readme里面的link想看看对应的blog，但是打开不了

请问博主queryInDatabaseDemo里的256feat2048Norml.mat或者256feat4096Norml.mat需要自己生成吗？自己改extractCNN这个文件？

首先感谢大佬的cnn case和各种hash benchmark！致敬！想请教下大佬，我用vgg提取了2048d的特征，在用hash索引的方法是不是不太好，我看到你用的是矩阵相乘排序的方式，因为我的图片大概有500多G 抽取下来的特征大概也有几个G，加载到内存有点太伤了，另外看到你关于CNN 抽取特征做PCA的实验非常感谢指点，这个也是个思路（有点好奇cnn输出的特征做dense输出和pca的效果），但是最终 有必要用hash搜索吗，是否会有很大的损失。目前我试过2048D 做LSH 效果 很不太好。

大神有没有评估过faiss在处理咱这一系列绕着image retrieval的工作中有多大实际的提升吗

I want to know how the compute cost and model size of this method.
does this method support to run on the mobile device?

hi ,
my error is :

res = vl_simplenn(net, im_) ;

"Attempt to execute SCRIPT vl_nnconv as a function:
C:\Users\Mehrdad\Source\Repos\CNN-for-Image-Retrieval\matconvnet-1.0-beta17\matlab\vl_nnconv.m"
how can i solve it?

Do you have the ESP Game dataset? If you have, would you give me the dataset？
Thank you.

具体修改地方为1和2。

楼主您好，请问您博客中的Pic Search 的demo- “CNN-Web-Demo-for-Image-Retrieval”. 还开放吗？ 链接好像失效了.....也没有找到，不知道可否发一下链接呢? 谢谢。

Error using -
Matrix dimensions must agree.
我有5000+张图片，跑到1982张的时候就报这个错误