https://github.com/kendricktan/rarepepes

Make your own rare pepes
https://github.com/kendricktan/rarepepes

Last synced: about 2 months ago
JSON representation

Make your own rare pepes

• Host: GitHub
• URL: https://github.com/kendricktan/rarepepes
• Owner: kendricktan
• License: mit
• Created: 2017-05-09T21:25:10.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2021-04-02T15:51:43.000Z (over 3 years ago)
• Last Synced: 2024-05-27T12:08:57.682Z (4 months ago)
• Language: Python
• Homepage: https://makerarepepes.me
• Size: 2.77 MB
• Stars: 22
• Watchers: 4
• Forks: 5
• Open Issues: 5
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# rarepepes

### Make your own rare pepes (inspired by [cyclegan-pix2pix](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix))

![Sample](https://i.imgur.com/O5MUs2h.png)

# Running locally

1. Download [pre-trained weights](https://www.dropbox.com/s/kxuz0ge75e9fsyx/rarepepes_checkpoints.tar.gz?dl=0) and extract it somewhere

2. Setup env

```

wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh

chmod +x conda.sh

./conda.sh  # Remember to add conda to the PATH variable

pip install flask scikit-image

conda install pytorch torchvision -c soumith

```

3. Run server with:

```

python app.py --checkpoints_dir PRE_TRAINED_WEIGHTS_LOCATION

```

# Dataset

The pepe dataset can be downloaded from [dropbox](https://www.dropbox.com/s/mgqiqermp0o9uzp/rarepepes_data.tar.gz?dl=0)

# References

1. [pix2pix](https://arxiv.org/abs/1611.07004)