| import os | |
| import gradio as gr | |
| from PIL import Image | |
| from huggingface_hub import hf_hub_url, cached_download | |
| os.system("git clone https://github.com/AK391/stylegan2-ada-pytorch") | |
| os.chdir("stylegan2-ada-pytorch") | |
| os.mkdir("outputs") | |
| os.mkdir("outputs/images") | |
| config_file_url = hf_hub_url("AUBMC-AIM/OCTaGAN", filename="OCTaGAN.pkl") | |
| cached_file = cached_download(config_file_url) | |
| def inference(truncation,seeds): | |
| os.system("python generate.py --outdir=./outputs/images/ --trunc="+str(truncation)+" --seeds="+str(int(seeds))+" --network="+cached_file) | |
| seeds = int(seeds) | |
| image = Image.open(f"./outputs/images/seed{seeds:04d}.png") | |
| return image | |
| title = "OCTaGAN" | |
| description = "Gradio demo for OCTaGAN. OCTaGAN is a GAN trained on wide-field corneal Optical Coherence Tomography (OCT) scans to generate cornea scans with a variety of pathologies (e.g.keratoconus disease) and surgical procedures (e.g. Implantable Collamer Lens (ICL) surgery, intrastromal corneal ring segment (ICRS) surgery, and Laser vision correction). OCTaGAN can be used for educational purposes as well as for generating training examples for ML algorithms." | |
| article = "<p style='text-align: center'><a href='https://cyrilzakka.github.io/radiology/2020/10/13/mammogenesis.html' target='_blank'>MammoGANesis: Controlled Generation of High-Resolution Mammograms for Radiology Education</a><center><a href='https://colab.research.google.com/drive/1vfbvMMkEBIwiuSbuC5pP-hsQr1nBmJXa?usp=sharing' target='_blank'><img src='https://colab.research.google.com/assets/colab-badge.svg' alt='Open In Colab'/></a></center></p><center><img src='https://visitor-badge.glitch.me/badge?page_id=AUBMC-AIM_octogan' alt='visitor badge'></center>" | |
| gr.Interface(inference,[gr.inputs.Slider(label="truncation",minimum=0, maximum=5, step=0.1, default=0.8),gr.inputs.Slider(label="Seed",minimum=0, maximum=1000, step=1, default=0)],"pil",title=title,description=description,article=article, examples=[ | |
| [0.8,0] | |
| ]).launch(enable_queue=True,cache_examples=True) |