kevinlin311tw/caffe-cvprw15
:heart::coffee: Deep Learning of Binary Hash Codes for Fast Image Retrieval (CVPRW15)
C++NOASSERTION
Issues
- 1
How to initialize weights by using LSH ?
#38 opened by PURE-melo - 1
- 0
Need help!
#20 opened by AemikaChow - 0
mnist dataset experiments
#40 opened by tkone2018 - 0
Can't down load the models and cfg
#39 opened by jia0511 - 2
error in demo.m
#33 opened by FartFang - 26
Hi,I follow the README to accomplish the run_cifar10.m.It said that I will got MAP=0.89 (about),but finnaly I got it about 0.1 .Is there anyone who hace the same problem with me or can give me some suggestion?thank you
#17 opened by iWeisskohl - 0
How to optimize?
#37 opened by lxq0204 - 3
trainning myself datasets
#35 opened by IvyYZ - 4
- 1
I couldn't download the KevinNet_CIFAR10_48.caffemodel with the related link
#36 opened by koalaofpoint - 11
About run_cifar10
#22 opened by MModerato - 1
- 2
I get an error “error=cudaSuccess(2 vs. 0) out of memory?” when training. how can i adjust some configuration or image dataset?
#30 opened by wzvoid - 1
- 3
- 1
- 1
why do you use imagenet's mean file on cifar-10? I think i should recreate mean file on my own image dataset,right? Hope to get your help.
#28 opened by wzvoid - 5
Is there a Python version of the code? I am learning something about image retrieval and not familiar with Matlab.
#25 opened by wzvoid - 2
about matcaffe_batch_feat
#24 opened by kli017 - 1
could someone help me with my issues
#16 opened by sjean - 9
Demo.m Error !!
#14 opened - 2
- 3
error in compiling matlab by /usr/local/MATLAB/R2014a/bin/mexext: Command not found
#32 opened by humengdoudou - 0
Could you open "the search with pure C/C++ implementation to compute hamming distance" codes?
#29 opened by shengwenliang - 3
Can this project support octive to replace matlab
#27 opened by zjjott - 0
do you mean that given a query image and a training dataset with 1 million images, the code needs to compare its hash codes with the training images 1 million times?
#15 opened by brisker - 0
Feature change strongely after Cropped image
#13 opened by mxq-151 - 2
The problem about finetuning
#12 opened by Saniya666 - 4
error when running train_48.sh
#11 opened by brisker - 2
- 2
- 0
Hello,Kevin!As for the other methods like KMH,LSH,PCA-ITQ etc, have you run the corresponding codes yourself or you just cite other researches' results?
#8 opened by brisker - 4
How to extract the features from fc7 layer?
#3 opened by sunyinhui - 2
How to fine-tune the existing CNN model?
#6 opened by sunyinhui - 0
- 0
Hashing for VGG network
#5 opened by CrossLee1 - 9
- 10
I have a question , please help!!!
#1 opened by sunyinhui - 5
How can i train my datas? ths
#2 opened by sunyinhui