Upload config.yaml with huggingface_hub

config.yaml

@@ -0,0 +1,57 @@
+# Problem A: Few-Shot Defect Classification - Configuration
+# Intel contest: 8 defect classes, grayscale images up to ~7000x5600
+# Uses ONLY official challenge data from challenge/dataset/Dataset/Data/
+# Dataset: defect1(253), defect2(178), defect3(9), defect4(14),
+#          defect5(411), defect8(803), defect9(319), defect10(674), good(7135)
+# Contest: classify into 8 DEFECT classes
+#
+# CRITICAL: defect3~defect9 (0.963 cosine sim) and defect4~defect8 (0.889)
+# are nearly identical without training on them. ALL 8 classes must be in
+# training so the backbone learns to separate these similar pairs.
+
+data:
+  root: "../challenge/dataset/Dataset/Data/"
+  img_size: 518                  # DINOv2 native resolution (37x14 patches)
+  defect_only: false
+  # ALL 8 defect classes + good (class 0) in training
+  train_classes: [0, 1, 2, 3, 4, 5, 8, 9, 10]
+  test_classes: [3, 4]           # Monitor the hardest classes during validation
+  all_classes: [0, 1, 2, 3, 4, 5, 8, 9, 10]
+
+model:
+  backbone: "dinov2"
+  backbone_size: "large"           # DINOv2 ViT-L/14 (1024-dim, 304M params)
+  freeze_backbone: true
+  unfreeze_last_n: 6               # Fine-tune last 6 transformer blocks + norm
+  grad_checkpointing: true
+  proj_hidden: 768
+  proj_dim: 512
+
+training:
+  n_way: 9                         # ALL 9 classes per episode (8 defect + good)
+  k_shot: 5                        # Higher shot count for better prototypes
+  n_query: 10                      # More queries = stronger gradient signal
+  # Sampler uses replacement for rare classes (defect3=9, defect4=14)
+  n_episodes_train: 500            # Fewer but harder 8-way episodes
+  n_episodes_val: 100
+  epochs: 100
+  lr: 3.0e-4
+  lr_backbone: 5.0e-6
+  warmup_epochs: 5
+  weight_decay: 1.0e-4
+  use_amp: true
+  gradient_clip: 1.0
+  label_smoothing: 0.1             # Prevent overconfidence on easy classes
+  patience: 20
+
+evaluation:
+  n_seeds: 5
+  max_examples: 50
+  kshot_values: [1, 3, 5, 10, 20]
+  target_accuracy: 0.85
+
+output:
+  checkpoint_dir: "checkpoints/"
+  results_dir: "outputs/"
+
+seed: 42