Python package to model and to perform topology optimization for graphene kirigami using deep learning. We use convolutional neural networks (similar to VGGNet architecure) for regression.
- Python script to create and test fine grid dataset from coarse grid dataset is avalaible in
bin\create-and-test-fine-grid.py
- Regression and optimization
- A python code to perform regression with TensorFlow is avalaible in
notebooks\CNN\01-regression.ipynb - A python code to perform search optimal design with TensorFlow is avalaible in
notebooks\CNN\02-search-designs.ipynb
- Dataset
- Raw dataset of coarse-grained configs is avaialble in
raw. This dataset generated using AIREBO potential with 1.7 mincutoff which is the default of CH.airebo.
This package is still under developement. More features will be added soon.
All dependencies are included in environment.yml file. We can either have environment setup in our own project directory
or in the envs directory of the miniconda folder. The advantage of installing in miniconda folder is that we can use same env
for different packages and it saves bandwidth and storage. The first method on the other hand is more robust. Prcedure is as follows
First of all if mamba do not exists then install it via
conda activate base
conda install mamba -n base -c conda-forgeTo setup env in project dir
mamba env create --prefix ./env --file environment.yml --forceor to setup in miniconda envs dir
mamba env create --name pytorch-1.12.0 --file environment.yml --forceIf you add (remove) dependencies to (from) the environment.yml file or the requirements.txt file after the environment has already been created, then you can re-create the environment with the following command.
To update env in project ./env dir
conda activate base
mamba env update --prefix ./env --file environment.yml --pruneTo update in Miniconda envs dir
conda actiavte base
mamba env update --name pytorch-1.12.0 --file environment.yml --pruneIf you are low on storage and want to completely remove the conda env. You can do it by
conda deactivate
conda env remove --prefix ./env
# or to remove from conda env dirs
conda env remove --name pytorch-1.12.0