NU-CUCIS/CrossPropertyTL
Cross-property Deep Transfer Learning
This tool helps materials scientists and researchers predict various material properties, like formation energy, for new compounds. You provide a list of chemical formulas, and the tool uses deep learning to output predictions for the desired property. It is designed for researchers working with materials data, especially when they have smaller datasets.
No commits in the last 6 months.
Use this if you need to predict material properties from chemical formulas, particularly when you have a limited amount of experimental or DFT-computed data for the specific property.
Not ideal if you are not working with materials property prediction or if you prefer traditional physics-based simulations over data-driven approaches.
Stars
9
Forks
4
Language
Jupyter Notebook
License
—
Category
Last pushed
Nov 16, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NU-CUCIS/CrossPropertyTL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...