Coder Social home page Coder Social logo

coincheung / triplet-reid-pytorch Goto Github PK

View Code? Open in Web Editor NEW
100.0 4.0 24.0 91.4 MB

My implementation of the paper [In Defense of the Triplet Loss for Person Re-Identification]

Home Page: https://arxiv.org/abs/1703.07737

License: Apache License 2.0

Python 99.60% Shell 0.40%
triplet reid pytorch

triplet-reid-pytorch's People

Contributors

coincheung avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

triplet-reid-pytorch's Issues

Large Gap in results across different trainings

Hi,
I used your code and changed the stride to 2 for faster computation.
I ran the training three times and got the following results in different runs:
Run1: mAP 74.2, cmc1: 86.1
Run2: mAP 64.7 cmc1: 80.5
Run3: mAP 75.2 cmc1: 87.5

As you see, in the second run the map and cmc1 dropped by large amount. I am not sure what is the reason for this.
Do you think this is because of the random erasing being used?
Have you also observed a large variation in results across different trainings?

Regards

The speed of batch sampler

I use the batch sampler in this repo, but the data fetch speed is quite slow, which is ~250s for 50 batches. The batch size is 256, P=32, K=8, use 4 workers and 4 GPUs. Have you encountered with this problem?

embed

for it, (img, lb_id) in enumerate(dl):
    print('\r=======>  processing iter {} / {}'.format(it, all_iter_nums),
            end = '', flush = True)
    label_ids.append(lb_id)
    #label_cams.append(lb_cam)
    embds = []
    for im in img:
        im = im.cuda()
        embd = model(im).detach().cpu().numpy() #通过网络生成特征向量
        embds.append(embd)
    embed = sum(embds) / len(embds)
    embeddings.append(embed)

请问代码为什么每次要把一个batch的特征求和除去长度

Low mAP on the market1501 dataset

Hi CoinCheung,

Thank you for you code. I have tested it on the market1501 dataset, the result is lower than the readme result:

mAP is: 0.525827546826, cmc is: [0.7185273]

Can you tell the what's wrong with it?

adjust the stride of last stage of resnet

Hi ! Thank you for your tricks, I would like to know what do you mean by saying "adjust the stride of the last stage of resnet from 2 to 1." Please let me know thank you

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.