| { | |
| "model_type": "attention_unet", | |
| "backbone": "convnext", | |
| "img_size": 256, | |
| "in_channels": 3, | |
| "out_channels": 1, | |
| "auto_map": { | |
| "AutoConfig": "modeling_attention_unet.AttentionUNetConfig", | |
| "AutoModel": "modeling_attention_unet.AttentionUNetForSegmentation" | |
| }, | |
| "training": { | |
| "loss": "bce_dice", | |
| "lr": 0.001, | |
| "weight_decay": 0.0001, | |
| "warmup_ratio": 0.05, | |
| "scheduler": "cosine", | |
| "batch_size": 64, | |
| "epochs": 50, | |
| "optimiser": "AdamW" | |
| }, | |
| "test_metrics": { | |
| "dice": 0.9411258697509766, | |
| "iou": 0.8887985348701477, | |
| "f1": 0.94112581440282, | |
| "precision": 0.9617935460534044, | |
| "recall": 0.9213276440087947, | |
| "accuracy": 0.9803045654296875, | |
| "loss": 0.0876474380493164 | |
| }, | |
| "dataset": "andreribeiro87/kvasir-seg-augmented", | |
| "note": "Best test-Dice model from architecture sweep (no HPO applied)" | |
| } |