Add CLIP fine-tuning pipeline for logo recognition

Implement contrastive learning with LoRA to fine-tune CLIP's vision
encoder on LogoDet-3K dataset for improved logo embedding similarity.

New training module (training/):
- config.py: TrainingConfig dataclass with all hyperparameters
- dataset.py: LogoContrastiveDataset with logo-level splits
- model.py: LogoFineTunedCLIP wrapper with LoRA support
- losses.py: InfoNCE, TripletLoss, SupConLoss implementations
- trainer.py: Training loop with mixed precision and checkpointing
- evaluation.py: EmbeddingEvaluator for validation metrics

New scripts:
- train_clip_logo.py: Main training entry point
- export_model.py: Export to HuggingFace-compatible format

Configurations:
- configs/jetson_orin.yaml: Optimized for Jetson Orin AGX
- configs/cloud_rtx4090.yaml: Optimized for 24GB cloud GPUs
- configs/cloud_a100.yaml: Optimized for 80GB cloud GPUs

Documentation:
- CLIP_FINETUNING.md: Training guide and usage instructions
- CLOUD_TRAINING.md: Cloud GPU recommendations and cost estimates

Modified:
- logo_detection_detr.py: Add fine-tuned model loading support
- pyproject.toml: Add peft, pyyaml, torchvision dependencies

configs/cloud_rtx4090.yaml

@@ -0,0 +1,64 @@
+# Training configuration optimized for cloud RTX 4090 / RTX 3090 (24GB VRAM)
+#
+# Usage:
+#   python train_clip_logo.py --config configs/cloud_rtx4090.yaml
+#
+# Estimated training time: 4-6 hours
+# Estimated cost on RunPod: ~$3
+
+# Base model
+base_model: "openai/clip-vit-large-patch14"
+
+# Dataset paths
+dataset_dir: "LogoDet-3K"
+reference_dir: "reference_logos"
+db_path: "test_data_mapping.db"
+
+# Data splits
+train_split: 0.7
+val_split: 0.15
+test_split: 0.15
+
+# Larger batches for faster training on 24GB VRAM
+batch_size: 32
+logos_per_batch: 32
+samples_per_logo: 4
+gradient_accumulation_steps: 4  # Effective batch = 128
+num_workers: 8
+
+# Model architecture
+lora_r: 16
+lora_alpha: 32
+lora_dropout: 0.1
+freeze_layers: 12
+use_gradient_checkpointing: true
+
+# Training
+learning_rate: 1.0e-5
+weight_decay: 0.01
+warmup_steps: 500
+max_epochs: 20
+mixed_precision: true
+
+# Loss
+temperature: 0.07
+loss_type: "infonce"
+triplet_margin: 0.3
+
+# Early stopping
+patience: 5
+min_delta: 0.001
+
+# Output
+checkpoint_dir: "checkpoints"
+output_dir: "models/logo_detection/clip_finetuned"
+save_every_n_epochs: 2  # Save more frequently for cloud
+
+# Logging
+log_every_n_steps: 10
+eval_every_n_epochs: 1
+
+seed: 42
+use_hard_negatives: false
+use_augmentation: true
+augmentation_strength: "medium"