demo.git - Vide-coded 64k demo system

Age	Commit message (Collapse)	Author
30 hours	CNN v2: Patch-based training as default (like CNN v1)	skal
	Salient point detection on original images with patch extraction. Changes: - Added PatchDataset class (harris/fast/shi-tomasi/gradient detectors) - Detects salient points on ORIGINAL images (no resize) - Extracts 32×32 patches around salient points - Default: 64 patches/image, harris detector - Batch size: 16 (512 patches per batch) Training modes: 1. Patch-based (default): --patch-size 32 --patches-per-image 64 --detector harris 2. Full-image (option): --full-image --image-size 256 Benefits: - Focuses training on interesting regions - Handles variable image sizes naturally - Matches CNN v1 workflow - Better convergence with limited data (8 images → 512 patches) Script updated: - train_cnn_v2_full.sh: Patch-based by default - Configuration exposed for easy switching Example: ./scripts/train_cnn_v2_full.sh # Patch-based # Edit script: uncomment FULL_IMAGE for resize mode Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
30 hours	Fix: CNN v2 training - handle variable image sizes	skal
	Training script now resizes all images to fixed size before batching. Issue: RuntimeError when batching variable-sized images - Images had different dimensions (376x626 vs 344x361) - PyTorch DataLoader requires uniform tensor sizes for batching Solution: - Add --image-size parameter (default: 256) - Resize all images to target_size using LANCZOS interpolation - Preserves aspect ratio independent training Changes: - train_cnn_v2.py: ImagePairDataset now resizes to fixed dimensions - train_cnn_v2_full.sh: Added IMAGE_SIZE=256 configuration Tested: 8 image pairs, variable sizes → uniform 256×256 batches Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>