-
Notifications
You must be signed in to change notification settings - Fork 218
[Example] Add TADF材料分子的光电性质预测 #974
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: develop
Are you sure you want to change the base?
Conversation
Thanks for your contribution! |
请起一个合适的标题 @YfB1125 ,并补充一下PR的简单描述 |
commit代码之前请安装pre-commit,并且使用pre-commit格式化代码,否则code-style-check CI无法通过 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
请参考建议修改代码细节
docs/zh/examples/tadf.md
Outdated
|
||
``` sh | ||
#Est 预测: | ||
cd TADF_angle |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这里写错文件名了
cd TADF_angle | ||
python angle.py | ||
cd ../ | ||
``` |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
评估命令应指明预训练模型权重路径,可参考其他案例格式
eval_during_train: False # | ||
batch_size: 8 # | ||
learning_rate: 0.0001 | ||
save_model_path: './est_model.pth' |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
pth是torch的模型名,建议修改为paddle格式
docs/zh/examples/tadf.md
Outdated
!!! note | ||
|
||
1. 开始训练、评估前,请先确保性质数据文件(.dat)和SMILES(smis.txt)数据文件的存在,并对应修改 yaml 配置文件中的 `data_dir` 为性质数据文件路径,`sim_dir` 为SMILES数据文件路径。 | ||
2. 如果需要使用预训练模型进行评估,请先下载预训练模型[Est.pdparams](https://paddle-org.bj.bcebos.com/paddlescience/models/TADF/Est/Est_pretrained.pdparams), [f.pdparams](https://paddle-org.bj.bcebos.com/paddlescience/models/TADF/f/f_pretrained.pdparams), 并对应修改 yaml 配置文件中的 `load_model_path` 为模型参数路径。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这里少了angle
eval_during_train: False # | ||
batch_size: 8 # | ||
learning_rate: 0.01 | ||
save_model_path: './angle_model.pdparams' |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
默认的路径和train默认的模型名不一致
examples/tadf/TADF_f/config/f.yaml
Outdated
# evaluation settings | ||
EVAL: | ||
test_size: 0.1 | ||
load_model_path: './f_pretrained.pdparams' |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
建议和train保存的模型名一致
docs/zh/examples/tadf.md
Outdated
#Est 评估: | ||
cd TADF_angle | ||
python Est.py | ||
cd ../ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
cd 这个命令可能没必要 有点冗余
已对文档和配置文件进行修改。请协助修改预训练模型参数的文件名,以保持训练和评估的模型参数文件名一致。我希望下载修改后模型文件的文件名为 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
预训练模型权重路径已修改,其他请参考review意见
test_size: 0.1 | ||
load_model_path: './angle_model.pdparams' | ||
seed: 20 | ||
pretrained_model_path: null |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
请检查三个yaml文件的运行脚本命令和该行字段,包括”EVAL“
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
三个yaml文件中与读取、保存模型参数的字段均已修改
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
文档(.md)也已经修改
…into dev_model
…into dev_model
TADF材料分子的光电性质预测
PR types
PR changes
Describe
有机发光二极管(OLED)具有高效率、结构灵活和低成本的优势,在先进显示和照明技术中受到广泛关注。在有机发光二极管器件中,电注入载流子以1:3的比例形成单线态和三线态激子。以纯荧光材料为发光材料构建的OLED发光效率IQE理论极限为25%。另一方面,有机金属复合物发光材料通过引入稀有金属(Ir,Pt等)带来强自旋轨道耦合(SOC),可以将单线态激子通过系间窜越过程转化成三线态激子,从而利用三线态激子发出磷光,其IQE可达100%,但是稀有金属价格昂贵,为推广使用带来了阻碍。热活化延迟荧光材料(TADF)为解决这些问题提供了新思路,并引起了广泛关注。在TADF中,三线态通过逆系间窜越过程(RISC)转化成单重态并发出荧光,从而实现100%的IQE,而RISC过程很大程度上取决于最低单线态(S1)和最低三线态(T1) 之间的能隙(ΔEST)。根据量子力学理论,ΔEST相当于HOMO和LUMO之间的交换积分的两倍。因此TADF分子的常见设计策略是将电子供体(D)和电子受体(A)以明显扭曲的二面角结合以实现HOMO和LUMO在空间上明显的分离。然而,与ΔEST相反,振子强度(f)需要较大的HOMO和LUMO之间的重叠积分,这二者之间的矛盾需要进一步平衡。