https://github.com/lamm-mit/dyfranet

https://github.com/lamm-mit/dyfranet

Last synced: about 1 year ago
JSON representation

• Host: GitHub
• URL: https://github.com/lamm-mit/dyfranet
• Owner: lamm-mit
• License: mit
• Created: 2022-09-06T12:26:44.000Z (almost 4 years ago)
• Default Branch: main
• Last Pushed: 2022-11-15T20:12:07.000Z (over 3 years ago)
• Last Synced: 2025-03-30T12:41:41.520Z (about 1 year ago)
• Language: Jupyter Notebook
• Size: 4.8 MB
• Stars: 7
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

          
# DyFraNet

![image](https://user-images.githubusercontent.com/101393859/202016081-178b33cc-6034-41b0-b656-83b56ae0ce83.png)

Reference: Yu-Chuan Hsu, Markus J. Buehler, DyFraNet: Forecasting and Backcasting Dynamic Fracture Mechanics in Space and Time Using a 2D-to-3D Deep Neural Network, in submission 

#### If you are using our dataset $immatrix\\_2D.npy$, you can simply run the python code to train the model by:

python3 main.py --batch_size 32 

#### If you are using your own dataset, you might need to specify the number of frames, $N$, for the input to train the model by:

python3 main.py --batch_size 32

                --numframe N

#### To download our pre-trained model, please download and unzip it to the currnet folder from the link below:

https://www.dropbox.com/s/9phk9osmzzpbh66/model.zip?dl=0

#### and then run $prediction.ipynb$ to explore the model with your own input.