File size: 5,024 Bytes
c31e9ec | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 | {
"preprocessing_version": "1.0.0",
"model_family": "car_body_shared",
"supported_candidates": [
{
"name": "EfficientNet-B0",
"timm_id": "efficientnet_b0",
"role": "primary_baseline",
"image_size": 224,
"crop_size": 224,
"notes": "Primary baseline. ~5.3M params, ~21 MB FP32. Mild augmentation sufficient."
},
{
"name": "MobileNetV3-Large",
"timm_id": "mobilenetv3_large_100",
"role": "active_candidate",
"image_size": 224,
"crop_size": 224,
"notes": "Lightweight CNN. ~5.5M params, ~22 MB FP32. Shares same preprocessing contract."
},
{
"name": "EfficientNetV2-S",
"timm_id": "tf_efficientnetv2_s",
"role": "active_candidate",
"image_size": 224,
"crop_size": 224,
"notes": "Improved EfficientNet. ~21.5M params, ~86 MB FP32. Within 95 MB limit."
},
{
"name": "ConvNeXt-V2-Atto",
"timm_id": "convnextv2_atto",
"role": "active_candidate",
"image_size": 224,
"crop_size": 224,
"notes": "Hybrid CNN/ViT macro-design. ~3.7M params, ~15 MB FP32. Ideal for small datasets."
},
{
"name": "EfficientNet-B3",
"timm_id": "efficientnet_b3",
"role": "active_candidate",
"image_size": 224,
"crop_size": 224,
"notes": "Larger EfficientNet. ~12M params, ~48 MB FP32. Within 95 MB limit."
},
{
"name": "ResNet-50",
"timm_id": "resnet50",
"role": "fallback",
"fallback_flag_required": true,
"image_size": 224,
"crop_size": 224,
"notes": "Classic CNN baseline. ~25M params, ~100 MB FP32 – exceeds 95 MB; requires quantization or FP16."
},
{
"name": "ConvNeXt-Tiny",
"timm_id": "convnext_tiny",
"role": "fallback",
"fallback_flag_required": true,
"image_size": 224,
"crop_size": 224,
"notes": "~28M params, ~112 MB FP32 – exceeds 95 MB; requires FP16 cast."
},
{
"name": "Swin-Transformer-Tiny",
"timm_id": "swin_tiny_patch4_window7_224",
"role": "fallback",
"fallback_flag_required": true,
"image_size": 224,
"crop_size": 224,
"notes": "~28M params, ~112 MB FP32 – exceeds 95 MB; requires FP16 cast (model.half())."
}
],
"image_size": 224,
"crop_size": 224,
"interpolation": "bicubic",
"interpolation_rationale": "Bicubic uses 4x4 pixel neighborhoods with cubic polynomials, preserving derivative continuity at vehicle edges (roofline, C-pillar, wheel arches). Bilinear blurs these high-frequency spatial features.",
"normalization": {
"type": "imagenet_zscore",
"mean": [0.485, 0.456, 0.406],
"std": [0.229, 0.224, 0.225],
"channels": "RGB",
"rationale": "ImageNet Z-Score normalization conditions the Hessian matrix (kappa(H) ≈ 1), producing a near-spherical loss landscape for stable gradient descent convergence."
},
"augmentation": {
"vertical_flip_enabled": false,
"vertical_flip_rationale": "FORBIDDEN. Creates physically impossible upside-down vehicles. Neural networks use gravity direction as implicit spatial reference; vertical flip destroys the structural hierarchy (wheels-down, roof-up) that distinguishes body types.",
"horizontal_flip": {
"probability": 0.5,
"rationale": "Safe. Aerodynamic symmetry means left/right views are label-invariant. Effectively doubles dataset size at zero semantic cost."
},
"random_resized_crop": {
"scale_min": 0.8,
"scale_max": 1.0,
"aspect_ratio_min": 0.95,
"aspect_ratio_max": 1.05,
"rationale": "Aspect-ratio locked to [0.95, 1.05]. Vehicle body type is defined by length-to-height ratio; extreme distortion can make a Sedan appear as a MICRO or Hatchback."
},
"rotation": {
"max_degrees": 10.0,
"padding_mode": "reflect",
"rationale": "Simulates camera tilt (±10°). Reflection padding avoids zero-pad corner artefacts that create spurious edge features in early conv layers. Rotation >15° risks same label-invariance violation as vertical flip."
},
"color_jitter": {
"brightness": 0.2,
"contrast": 0.2,
"saturation": 0.2,
"hue": 0.1,
"probability": 0.5,
"rationale": "Breaks spurious color correlations: MICRO cars tend to have bright colors; F1/Open-Wheel cars are often red (sponsor liveries). Forces model to learn chassis geometry, not color shortcuts."
}
},
"transform_contract": {
"train": "get_train_transforms() – includes all augmentation above",
"validation": "get_val_transforms() – deterministic: Resize + CenterCrop + ToTensor + Normalize",
"evaluation": "get_eval_transforms() – identical to validation",
"inference_api": "get_inference_transforms() – identical to validation; Phase 5 API imports this"
},
"class_count": 8,
"class_slugs": [
"SUV",
"VAN",
"STATION_WAGON",
"MICRO",
"ACIK_TEKERLEKLI_F1_ARACLARI",
"SEDAN",
"HATCHBACK",
"PICK_UP"
]
}
|