marcelhuber/KermanyV3_original-mirror-auto1-bgcfnc

KermanyV3 GAN Model

Description

The KermanyV3 GAN is a Generative Adversarial Network trained on the KermanyV3_original dataset to generate synthetic medical images.

Files Included

• fakes001020.png: Sample of synthetic images generated by the GAN at snapshot 001020.
• log.txt: Log file containing training progress and details.
• metric-fid50k_full.jsonl: JSONL file with FID (Fréchet Inception Distance) metric scores for evaluating image quality.
• metric-kid50k_full.jsonl: JSONL file with KID (Kernel Inception Distance) metric scores for evaluating image quality.
• network-snapshot-001020.pkl: Snapshot of the GAN's trained parameters at iteration 001020.
• stats.jsonl: JSONL file containing statistics and metrics related to the training process.
• training_options.json: JSON file detailing the training hyperparameters and options.

Dataset Used

KermanyV3_resized

Model Performance

• FID Score: 8.745657893911403
• KID Score: 0.005549223578578

Training Details

• Training Iterations: 001020
• Training Time: 11h 06m
• Architecture: StyleGAN2-ADA-PyTorch
• Batch Size: 16

Usage Instructions

1. Load the pre-trained GAN parameters from network-snapshot-001020.pkl.
2. Use the generator to generate synthetic images.
3. To evaluate image quality, refer to metric-fid50k_full.jsonl for FID scores and metric-kid50k_full.jsonl for KID scores.
4. For additional training information, refer to log.txt, stats.jsonl, and training_options.json.