Multi-pass-GAN

KO | EN

gitlite — search

#javascript #llm #go #machine-learning #rust #deep-learning #linux #macos #nodejs #java #kubernetes #awesome-list #security #openai

(★ 20)

Source code for SCA paper "A Multi-Pass GAN for Fluid Flow Super-Resolution"

Multi-pass-GAN Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Multi-pass-GAN

Public source code for the SCA paper "A Multi-Pass GAN for Fluid Flow Super-Resolution". Authors: Maximilian Werhahn, You Xie, MengYu Chu, Nils Thuerey. Technical University of Munich.

Paper: https://arxiv.org/pdf/1906.01689.pdf,  
Video: https://www.youtube.com/watch?v=__WE22dB6AA

![An example of our 8x model (low-res left, ours right)](https://raw.githubusercontent.com/maxwerhahn/Multi-pass-GAN/master/resources/teaser5.png)

## Requirements  
  
tensorflow >= 1.10  
mantaflow for datagen

## Directories  
`../datagen/`:			data generation via mantaflow  
`../GAN/`:					output + training + network files  
`../tools_wscale/`:	helper functions, data loader, etc.

## Compilation  
First, compile mantaflow with numpy support (as usual), follow 
http://mantaflow.com/install.html.
One difference is, in the CMake settings, numpy shoule be enabled: 
"cmake .. -DGUI=ON -DOPENMP=ON -DNUMPY=ON".
Note that if mantaflow is installed on a remote server, GUI is not supported, i.e.:
"cmake .. -DGUI=OFF -DOPENMP=ON -DNUMPY=ON".

## Data Generation  
Either use the file `../datagen/gen_mul_data.py` or similar commands for the file `../datagen/gen_sim_grow_slices_data.py` to generate a dataset. It will be stored in `../data3d_growing/sim_%04d`.

## Training  
Call `../GAN/example_run_training.py`

## Applying models
Call `../GAN/example_run_output.py`, pretrained models can be found in the branch "models"

Multi-pass-GAN

Multi-pass-GAN Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Multi-pass-GAN

Multi-pass-GAN Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README