diff options
Diffstat (limited to 'cnn_v3/docs/HOW_TO_CNN.md')
| -rw-r--r-- | cnn_v3/docs/HOW_TO_CNN.md | 30 |
1 files changed, 18 insertions, 12 deletions
diff --git a/cnn_v3/docs/HOW_TO_CNN.md b/cnn_v3/docs/HOW_TO_CNN.md index 624deaa..f5f1b1a 100644 --- a/cnn_v3/docs/HOW_TO_CNN.md +++ b/cnn_v3/docs/HOW_TO_CNN.md @@ -107,15 +107,6 @@ The network learns the mapping `albedo → target`. If you pass the same image a input and target, the network learns identity (useful as sanity check, not for real training). Confirm `target.png` looks correct before running training. -**Alternative — pack without a target yet:** -```bash -python3 pack_photo_sample.py \ - --photo /path/to/photo.png \ - --output dataset/simple/sample_001/ -# target.png defaults to a copy of the input; replace it before training: -cp my_stylized_version.png dataset/simple/sample_001/target.png -``` - **Batch packing:** ```bash for f in photos/*.png; do @@ -336,10 +327,22 @@ uv run train_cnn_v3.py \ --epochs 500 ``` +**Single-sample training (overfit on one input/target pair):** +```bash +# Pack first +./gen_sample.sh input/photo.png target/photo_styled.png dataset/simple/sample_001/ + +# Train — --full-image and --batch-size 1 are implied +uv run train_cnn_v3.py \ + --single-sample dataset/simple/sample_001/ \ + --epochs 500 +``` + ### Flag reference | Flag | Default | Notes | |------|---------|-------| +| `--single-sample DIR` | — | Train on one sample dir; implies `--full-image`, `--batch-size 1` | | `--input DIR` | `training/dataset` | Dataset root; always set explicitly | | `--input-mode` | `simple` | `simple`=photos, `full`=Blender G-buffer | | `--epochs N` | 200 | 500 recommended for full-image mode | @@ -356,6 +359,7 @@ uv run train_cnn_v3.py \ | `--film-cond-dim N` | 5 | Must match `CNNv3FiLMParams` field count in C++ | | `--checkpoint-dir DIR` | `checkpoints/` | Set per-experiment | | `--checkpoint-every N` | 50 | 0 to disable intermediate checkpoints | +| `--resume [CKPT]` | — | Resume from checkpoint path; if path missing, uses latest in `--checkpoint-dir` | ### Architecture at startup @@ -564,10 +568,12 @@ It owns: ``` SEQUENCE 0 0 "Scene with CNN v3" - EFFECT + GBufferEffect prev_cnn -> gbuf_feat0 gbuf_feat1 0 60 - EFFECT + CNNv3Effect gbuf_feat0 gbuf_feat1 -> sink 0 60 + EFFECT + GBufferEffect source -> gbuf_feat0 gbuf_feat1 0 60 + EFFECT + CNNv3Effect gbuf_feat0 gbuf_feat1 -> sink 0 60 ``` +Temporal feedback (`prev_cnn`) is wired automatically by `wire_dag()` — no explicit input needed in the `.seq` file. + Or direct C++: ```cpp #include "cnn_v3/src/cnn_v3_effect.h" @@ -658,7 +664,7 @@ Do not reference them from outside the effect unless debugging. ```bash cmake -B build -DCMAKE_BUILD_TYPE=Release cmake --build build -j4 -./build/demo +./build/demo64k ``` ### Expected visual output |