Code Monkey home page Code Monkey logo

asen's People

Contributors

zju-zhangy 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

Watchers

 avatar  avatar  avatar  avatar  avatar

asen's Issues

queries related to asen

  1. Can you please guide me through the steps to run the inference of the model with pretrained weights (i.e without downloading the deepfashion2, DARN or fashionai datasets)?

  2. Is running inference possible with the code given or i have to do any modification in the main.py file to run the demo(inference)?

  3. I have tried downloading DARN dataset, but it took me around 193gb for just 40k images where as the total images mentioned is around 2 lakhs , am i doing something wrong?

  4. Could you please point me to the links, where i can download the DARN dataset / fashionai dataset directly (please share the links to [email protected] , if you dont want share them publicly)?

Thanks,
Awaiting for a quick response.

General queries

Dear @Maryeon

Firstly thanks a lot for publishing the ASEN code , & a hearty congratulation for your paper publication your paper and model seems pretty robust and achieves a quite decent MAP score on multiple fashion dataset, I am working on fine grain attribute prediction for fashion image classification and retrieval. I wish to use ASEN code as a part of research purpose for the mentioned tasks. I wish to understand the code in detail, I am facing issues with dataset availability. For Fashion AI and DARP, It would be very kind of you if you could help me in giving some insights, help books, documentation or code go through so that I could implement in Colab notebook. Or please let me know if you have other mediums where I could reach out to you .

Thanking you

Ajay

clarity on Data preparation steps of DeepFashion Dataset

Hi , @Maryeon @ZJU-ZhangY ,
after preparing the deepfashion dataset, i am getting an error while training the model, below are the steps, i followed for deepfashion dataset preparation:

  1. Downlaoded the dataset split by running the code:
    wget -c -P data/ http://www.maryeon.com/file/meta_data.tar.gz
    cd data/
    tar -zxvf meta_data.tar.gz

  2. Deepfashion Dataset:
    Extracted the images of category and attribute prediction benchmark/img/img.zip and moved them to ./asen/data/DeepFashion/img

The file structure is:
data structure

questions:

  1. is the steps correct for data preparation?

  2. is the meta.json file should be in the structure data/meta.json or in data/DeepFashion/meta.json ?
    metajson structure

How to do interference for 1 random image from the internet?

Thanks for your contribution!

I was wondering how do I start changing the code to allow for inference of any fashion image url from the internet?

In the code I can see this:
masked_embedding = test_model(img, c)

where c: Integer indicating according to which attribute images are compared

What is c for a random fashion image from the internet?

Pre-trained weights

Hello.

I admire your work :)

Thank you for sharing great work.

I have a little question.

Do you have any plans to share your pre-trained weights of the DeepFashion dataset or other dataset?

Thank you.

Pretrained weights (ASEN)

Thank you for sharing great work!

I downloaded the pre-trained ASEN weights via your asenpp github repository.

However, I received an error when extracting .tar files (DARN.pth.tar, FashionAI.pth.tar, and DeepFashion.pth.tar).

I think that the files are broken.

Would you consider releasing the trained network parameters again?

Thank you!

Trained network parameters

Hi, thank you for sharing this great work!
I hope to run the model, but it seems that the trained weight is not released.
Would you consider releasing the trained network parameters to public? Thank you!

Performance on DARN

Hi, I trained the ASENet_V2 on the DARN dataset with the default arguments in README (python main.py --model ASENet_V2 --decay_rate 0.9 --step_size 3 --epochs 50), but it seems that the performance is inferior than that reported in Table 2.
Could you give me some suggestions about how to train the model (ex. hyperparameter settings)?

The screenshot after 50 epochs:
截圖 2020-07-14 上午10 46 52

License of code?

Hi @Maryeon ,

What's the license for this code? I looked at the files but didn't find anything and so I'm confused on how you'd like it to be used.

about DARN dataset

hi @Maryeon
thanks for sharing the links of DARN dataset, but it seems that some like can be reached. For example,
http://gi3.md.alicdn.com/bao/uploaded/i3/740472594/T2MSR1Xp4XXXXXXXXX_!!740472594.jpg RETURN 404
http://gi2.md.alicdn.com/bao/uploaded/i2/770282689/T2W7KVXvpaXXXXXXXX_!!770282689.jpg RETURN 404
http://gi2.md.alicdn.com/bao/uploaded/i2/737540216/T2aQhGXthXXXXXXXXX_!!737540216.jpg RETURN 404
http://gi2.md.alicdn.com/bao/uploaded/i2/666715352/T21wxGXvRaXXXXXXXX_!!666715352.jpg RETURN 404
http://gi4.md.alicdn.com/bao/uploaded/i4/666715352/T2FPBsXw8aXXXXXXXX_!!666715352.jpg RETURN 404
http://gi3.md.alicdn.com/bao/uploaded/i3/216195353/T2jzpCXElXXXXXXXXX_!!216195353.jpg RETURN 404

Even if I open the link with web browser, the image will not be displayed. Are these links out of order? Could you pls update the links or upload all the images to googledrive?

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.