Comments (20)
Combining softmax loss with metric learning loss to speed up the convergence is also a popular method.
from alignedreid-re-production-pytorch.
open-reid,batch size 256可以跑到rank-1 84.5%,参考这里. 印象中应该是在open-reid划分的Market1501上跑的实验,而不是在标准划分上跑的。
虽然我用Python 2跑的,你可以换成Python 3试一下,如果还不行那有可能跑出来就是那样吧。
也可以参考一下我这个工程里的一些设定,和open-reid稍有不同。进一步我做了一个小trick,可以跑到89%。
分类loss和triplet loss结合我还是没解决,你什么时候解决了跟我说一下,3q : )
from alignedreid-re-production-pytorch.
我试过2块显卡跑256batch size 还是低了几点,跑不到那个水平。
谢谢你了!
from alignedreid-re-production-pytorch.
hi
how about your triplet loss?
above is my loss result , is it right ? the value is small?
Train loss is triplet loss
Step: 79, Learning rate: 0.009942, Train loss: 0.157365
('pos_loss : ', 0.80680853)
('neg_loss : ', 1.0257512)
Step: 5409, Learning rate: 0.007231, Train loss: 0.057204
('pos_loss : ', 1.3745451)
('neg_loss : ', 1.9384971)
from alignedreid-re-production-pytorch.
@huanghoujing 您这里的trick具体是指什么呢
from alignedreid-re-production-pytorch.
@liliangqi 这里的trick就是把残差网络conv5的stride从2改为1,这样改过之后average pooling之前特征的分辨率就加倍了. 这个增加分辨率的做法是从文章Beyond Part Models: Person Retrieval with Refined Part Pooling看到的。
from alignedreid-re-production-pytorch.
@Phoebe-star I think your loss value 0.057204
is not small enough yet. You can also calculate how many triplets satisfy the margin inequality distance(anchor, positive) + margin < distance(anchor, negative)
, which I think is a better indicator.
from alignedreid-re-production-pytorch.
@huanghoujing 大神有没有看过Harmonious Attention Network for Person Re-identification 这篇文章,如果有的话,我想请教些问题。
from alignedreid-re-production-pytorch.
Step: 5409, Learning rate: 0.007231, Local Train loss: 0.29
('local pos_loss : ', 12.745451)
('local neg_loss : ', 11.384971)
I find the local feature doesn't effect .
the local feature use the
S (7 ,7) is the final distance , but its value is big , like 12.46782 or 11.14258
I think your local feature ,it is doing 7x7 =49 times, because you use the " for loop" (python) ,
but I watch the image in the paper , "AlignedReID: Surpassing Human-Level Performance in Person Re-Identificat"
it seem like do 7+6+5+4+3+2+1=28 times
answer can English or 中文 ,thanks
from alignedreid-re-production-pytorch.
@Phoebe-star The paper explains how to calculate the shortest distance well, and I just follow the paper. So any other explanation I would like to give here is just a duplicate. Maybe I wouldn't be able to get things right for you. Sorry for that.
from alignedreid-re-production-pytorch.
@Niculuse 不要称呼大神(逃
我觉得你直接问论文作者比较好,由于论文篇幅有限,作者肯定也有很多细节没机会详细解释,所以正是可以请教的地方。问我的话,我只能乱猜。
from alignedreid-re-production-pytorch.
@huanghoujing 好的,感谢!
from alignedreid-re-production-pytorch.
ok, thank you ,huanghoujing
but my local loss is right? It is a big value 12.745451 , the training step is about 5409 or 10000
local pos_loss : ', 12.745451)
sorry,because I can not test your network, I can not see your local value.
from alignedreid-re-production-pytorch.
If this value 12.745451
is loss, then it's large.
from alignedreid-re-production-pytorch.
how about your local loss?
from alignedreid-re-production-pytorch.
Similar to global loss, local loss can also decreases to near 0, e.g. 0.0003.
from alignedreid-re-production-pytorch.
I know the local loss will be decreases to near 0. how about the positive local loss and the negative local loss?
where is the local loss compute method ? I find you design two method . one is numpy ,another is torch
from alignedreid-re-production-pytorch.
#2
hi ,you say " distance of two unit-length vectors falls in range [0, 2], "
why not in the [0,1]? because normalization
and why after Equation (1), the distance is in range [0, 0.76]?
thanks you , god
from alignedreid-re-production-pytorch.
您好,请问一下分类loss和triplet loss结合会遇到什么问题呢?
from alignedreid-re-production-pytorch.
两个loss结合理论上会更好。但是我在Triplet Loss的performance已经很高的设定下再加分类loss,结果并没有提升,我弄不好这个。
from alignedreid-re-production-pytorch.
Related Issues (20)
- top-k结果可视化 HOT 2
- CUHK03和DUKE上的识别率 HOT 1
- How to inference my own test set
- Keys not found in source state_dict HOT 1
- Global Feature Extraction HOT 1
- Local feature dimensions
- About performance on market1501 for global learning and mutual learning
- Is it generalised
- TypeError: __init__() got an unexpected keyword argument 'log_dir'
- AssertionError HOT 3
- 请问论文中的Resnet50-Xception结构是不是没有实现? HOT 1
- 论文复现的参数问题
- how to use the test data to draw picture just like roc missrate cmc?
- How to use without GPU? HOT 2
- could you send me a partitions.pkl about market1501 HOT 1
- 为啥用你提供的weight测得market也只有88.78的top1呢 HOT 1
- how to infer some images or videos
- RuntimeError: cannot perform reduction function min on tensor with no elements because the operation does not have an identity
- Poor performnace when reproducing evaluation on market1501 HOT 2
- would you help me to fix this error?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from alignedreid-re-production-pytorch.