patchGAN image segmentation model in PyTorch

Project description

patchGAN

UNet-based GAN model for image segmentation using a patch-wise discriminator. Based on the pix2pix model.

Install the package with pip:

pip install patchgan

Upgrading existing install:

pip install -U patchgan

Get the current development branch:

pip install -U git+https://github.com/ramanakumars/patchGAN.git

You can train the patchGAN model with a config file and the patchgan_train command:

patchgan_train --config_file train_coco.yaml --n_epochs 100 --batch_size 16

See examples/train_coco.yaml for the corresponding config for the COCO stuff dataset.

This version

0.2

Aug 22, 2023

0.1

Jul 30, 2023

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Uploaded Aug 22, 2023 Source

Uploaded Aug 22, 2023 Python 3

Details for the file patchGAN-0.2.tar.gz.

Hashes for patchGAN-0.2.tar.gz
Algorithm	Hash digest
SHA256	`bfd1d43090d8ed997d613d4d982e925a3dd3054fd77484607a4ae74a52eb263d`
MD5	`240be8795ee937fb0da5e7fea8b1b34d`
BLAKE2b-256	`e5f9a5fca9ecbf5a518c45cb2a0c92d3f5b275464980a32b1910ea777cb4c450`

Details for the file patchGAN-0.2-py3-none-any.whl.

Hashes for patchGAN-0.2-py3-none-any.whl
Algorithm	Hash digest
SHA256	`207bdbbee9a87b00886eb2560448a169bdb55c749a862a48092ceaac841c3585`
MD5	`00ceb6c3c99e6f889a5108f0639d3f21`
BLAKE2b-256	`099a2fefc490a1ac63d659ac401b139e300c102b896ba927f394cd6dff8bbfa5`