We lifted 11 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| KarthiVi95/discoGAN_pytorch_implementation | reimplementation | 1 of 2 |
| S-HuaBomb/DiscoGAN-Paddle | pwc_unofficial | 0 of 9 |
| Function | Status | Where it lives |
|---|---|---|
| to_numpy | Ran | KarthiVi95/discoGAN_pytorch_implementation/discogan/discogan.py pointer only (licence: NONE) · get_code("334c0b12ef01ad4c") |
| as_np | Not yet run | S-HuaBomb/DiscoGAN-Paddle/discogan/image_translation.py code served (permissive licence) · get_code("9100398fafc3dddf") |
| fashionGenSetup | Not yet run | S-HuaBomb/DiscoGAN-Paddle/crop_celeba.py code served (permissive licence) · get_code("62e7050d48a0e93d") |
| get_celebA_files | Not yet run | S-HuaBomb/DiscoGAN-Paddle/discogan/dataset_demo.py code served (permissive licence) · get_code("9b157c4922ff25a5") |
| get_image_paths | Not yet run | KarthiVi95/discoGAN_pytorch_implementation/discogan/discogan.py pointer only (licence: NONE) · get_code("10668d307dead964") |
| get_logger | Not yet run | S-HuaBomb/DiscoGAN-Paddle/discogan/image_translation.py code served (permissive licence) · get_code("29c35b8fd91ab7df") |
| pil_loader | Not yet run | S-HuaBomb/DiscoGAN-Paddle/crop_celeba.py code served (permissive licence) · get_code("1f190f167dbdf92e") |
| read_attr_file | Not yet run | S-HuaBomb/DiscoGAN-Paddle/discogan/dataset.py code served (permissive licence) · get_code("c6650be7430c3a0a") |
| read_attr_file | Not yet run | S-HuaBomb/DiscoGAN-Paddle/discogan/dataset_demo.py code served (permissive licence) · get_code("74d1d08626444b0d") |
| read_images | Not yet run | S-HuaBomb/DiscoGAN-Paddle/discogan/dataset_demo.py code served (permissive licence) · get_code("1cb7a2c94a9c90a2") |
| saveImage | Not yet run | S-HuaBomb/DiscoGAN-Paddle/crop_celeba.py code served (permissive licence) · get_code("09407c9d23687689") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
While humans easily recognize relations between data from different domains without any supervision, learning to automatically discover them is in general very challenging and needs many ground-truth pairs that illustrate the relations. To avoid costly pairing, we address the task of discovering cross-domain relations given unpaired data. We propose a method based on generative adversarial networks that learns to discover relations between different domains (DiscoGAN). Using the discovered relations, our proposed network successfully transfers style from one domain to another while preserving key attributes such as orientation and face identity. Source code for official implementation is publicly available https://github.com/SKTBrain/DiscoGAN
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1703.05192")
get_code_for_paper("1703.05192")
have("1703.05192")
Connect an agent — have() is free.