diff options
| author | skal <pascal.massimino@gmail.com> | 2026-03-22 10:48:50 +0100 |
|---|---|---|
| committer | skal <pascal.massimino@gmail.com> | 2026-03-22 10:48:50 +0100 |
| commit | e323d793e76dec7576546068f9f4c7d8d8a1d34d (patch) | |
| tree | aa84934a39bcf7d65b642e5460048edd52bec83c /cnn_v3/docs | |
| parent | 4c7ca0f06eb180f4a83641466014865c334e8987 (diff) | |
fix(cnn_v3): resize target to albedo dims when sizes differ
target.png can have a different resolution than albedo.png in simple
samples; patch slicing into the smaller target produced 0×0 tensors,
crashing torch.stack in the DataLoader collate.
handoff(Gemini): target resized in _load_sample (LANCZOS) + note in HOW_TO_CNN §1c.
Diffstat (limited to 'cnn_v3/docs')
| -rw-r--r-- | cnn_v3/docs/HOW_TO_CNN.md | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/cnn_v3/docs/HOW_TO_CNN.md b/cnn_v3/docs/HOW_TO_CNN.md index bb6f7a7..56ee101 100644 --- a/cnn_v3/docs/HOW_TO_CNN.md +++ b/cnn_v3/docs/HOW_TO_CNN.md @@ -274,6 +274,7 @@ dataset/ - If `simple/` or `full/` subdir is absent the dataloader scans the root directly - Minimum viable dataset: 1 sample (smoke test only); practical minimum ~50+ for training - You can mix Blender and photo samples in the same subdir; the dataloader treats them identically +- `target.png` may differ in resolution from `albedo.png` — the dataloader resizes it to match albedo automatically (LANCZOS) --- |