Comments (4)
This assert is used to check if your trained DeepH models include all possible orbital combinations. Please review the orbital
parameters in your training ini settings to identify which orbitals are missing.
from deeph-pack.
Hi,
Many thanks for your quick reply. I checked the orbital basis that I used for training. It looks like the orbital basis is not right. If my orbital basis setting is Te7.0-s3p2d2f1, The number of orbital basis would be 31+23+52+71=26, right? Becase I used the python code (get_all_orbital_str.py) to produce the orbital parameter. The code needs we input the number of orbital basis.
Another question is whether the orbital number would increase the training time a lot if I use the same other parameters.
best regards,
Tao
from deeph-pack.
Yes, the number of orbits for this element is 26. Increasing the number of orbits will increase the training time per epoch, but not significantly.
Alternatively, you can choose to train a new model with only the additional orbits that the old model lacks. Then, when running deeph-inference
, you can specify the trained_model_dir
parameter in the configuration file to include both your new model and the old model.
from deeph-pack.
ok, many thanks for your help.
from deeph-pack.
Related Issues (20)
- error while 1.parse_Overlap in interfere part HOT 8
- question about step4_overlap HOT 1
- error while preprocess in demo-abacus HOT 2
- failure while preprocess in demo-abacus HOT 6
- deeph-inference --config inference.ini error for ABACUS3.0.0 HOT 1
- How to restart training model HOT 2
- how to run the code in windows system HOT 1
- failure when i run the process HOT 5
- how much time do we need in 1_DFT_calculation HOT 1
- I have a problem when i inference hamiton HOT 9
- how to get fermi energy HOT 1
- I get a problem with loss=0 in 3_train progess HOT 3
- why i trained 100 data ,the train loss is 0
- how to plot the result of the dft
- when is the code of the deepH-2 coming out HOT 1
- Interfacing with Abacus: assert "atom" in f.readline()
- requirement for training on GPU
- "IndexError: index out of range in self " while training HOT 2
- ArrayMemoryError: Unable to allocate 6.03 TiB for an array with shape (910224, 910224) and data type float64
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deeph-pack.