diff options
| author | skal <pascal.massimino@gmail.com> | 2026-02-12 11:48:02 +0100 |
|---|---|---|
| committer | skal <pascal.massimino@gmail.com> | 2026-02-12 11:48:02 +0100 |
| commit | c878631f24ddb7514dd4db3d7ace6a0a296d4157 (patch) | |
| tree | a24ccffc8997a7e0cc0270c59c599ef44d0086a8 /training/target_1/img_001.png | |
| parent | f4ef706409ad44cac26abb46fe8b2ddb78ec6a9c (diff) | |
Fix: CNN v2 training - handle variable image sizes
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>
Diffstat (limited to 'training/target_1/img_001.png')
0 files changed, 0 insertions, 0 deletions