Git Product home page Git Product logo

idtoolkit's Introduction

Hi, I'm Thyrix(Jia-Qi Yang)

idtoolkit's People

Contributors

thyrixyang avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

Forkers

shercklo

idtoolkit's Issues

Env Multi_Layer and function search

First I want to notice that the downloadable dataset Multi_Layer has a different size than the one indicated in the paper. That is $44400$ from the zip vs $60700$ claimed in the paper. Then, by running a simple experiment with your script main.py raises a ValueError.

python experiments/main.py --env multi_layer --dataset_path datasets/multi_layer --eval_method real_target --method cvae --method_config experiments/configs/cvae

The issue is due to the CombineSpace which is not all_numerical.

Traceback (most recent call last):
  File "IDToolkit/experiments/main.py", line 194, in <module>
    main(args)
  File "IDToolkit/experiments/main.py", line 105, in main
    pred_params = alg.search(num_samples=args.pred_num)
  File "IDToolkit/inverse_design_benchmark/algorithms/neural_opt.py", line 101, in search
    params = [self.env.parameter_space.from_numpy(p) for p in pred_params]
  File "IDToolkit/inverse_design_benchmark/algorithms/neural_opt.py", line 101, in <listcomp>
    params = [self.env.parameter_space.from_numpy(p) for p in pred_params]
  File "IDToolkit/inverse_design_benchmark/parameter_space/combine.py", line 72, in from_numpy
    raise ValueError("Only support converting numerical parameters from numpy")
ValueError: Only support converting numerical parameters from numpy

Are you aware of that ? Is there any workaround ? Thanks

Some questions about the substitute models for SCF

Dear Professor:
I have used the GBDT checkpoints for SCF provided by you, but the results from the proxy model are quite different from the real calculated results. What is the reason for this?
The following figure shows the specific configuration and results
微信图片_20230612110511
微信图片_20230612110516
微信图片_20230612110519

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.