diff options
| -rw-r--r-- | doc/CNN_V2.md | 21 | ||||
| -rwxr-xr-x | training/gen_identity_weights.py | 13 |
2 files changed, 30 insertions, 4 deletions
diff --git a/doc/CNN_V2.md b/doc/CNN_V2.md index 577cf9e..abef606 100644 --- a/doc/CNN_V2.md +++ b/doc/CNN_V2.md @@ -136,6 +136,27 @@ let bias = 1.0; // Learned bias per output channel // Packed storage: [p0, p1, p2, p3, uv.x, uv.y, sin(20*uv.y), 1.0] ``` +### Input Channel Mapping + +**Weight tensor layout (12 input channels per layer):** + +| Input Channel | Feature | Description | +|--------------|---------|-------------| +| 0-3 | Previous layer output | 4D RGBA from prior CNN layer (or input RGBD for Layer 0) | +| 4-11 | Static features | 8D: p0, p1, p2, p3, uv_x, uv_y, sin20_y, bias | + +**Static feature channel details:** +- Channel 4 → p0 (RGB.r from mip level) +- Channel 5 → p1 (RGB.g from mip level) +- Channel 6 → p2 (RGB.b from mip level) +- Channel 7 → p3 (depth or RGB channel from mip level) +- Channel 8 → p4 (uv_x: normalized horizontal position) +- Channel 9 → p5 (uv_y: normalized vertical position) +- Channel 10 → p6 (sin(20*uv_y): periodic encoding) +- Channel 11 → p7 (bias: constant 1.0) + +**Note:** When generating identity weights, p4-p7 correspond to input channels 8-11, not 4-7. + ### Feature Rationale | Feature | Dimension | Purpose | Priority | diff --git a/training/gen_identity_weights.py b/training/gen_identity_weights.py index 5756e67..5d83bfb 100755 --- a/training/gen_identity_weights.py +++ b/training/gen_identity_weights.py @@ -7,8 +7,8 @@ Output Ch{0,1,2,3} = Input Ch{0,1,2,3} (ignores static features). With --mix: Output Ch{i} = 0.5*Input Ch{i} + 0.5*Input Ch{i+4} (50-50 blend, avoids overflow) -With --p47: Output Ch{i} = Input Ch{i+4} (static features only) - (p4→ch0, p5→ch1, p6→ch2, p7→ch3) +With --p47: Output Ch{i} = static p{4+i} (uv_x, uv_y, sin20_y, bias) + (p4/uv_x→ch0, p5/uv_y→ch1, p6/sin20_y→ch2, p7/bias→ch3) Usage: ./training/gen_identity_weights.py [output.bin] @@ -26,7 +26,10 @@ def generate_identity_weights(output_path, kernel_size=1, mip_level=0, mix=False """Generate identity weights: output = input (ignores static features). If mix=True, 50-50 blend: 0.5*p0+0.5*p4, 0.5*p1+0.5*p5, etc (avoids overflow). - If p47=True, transfers p4→p0, p5→p1, p6→p2, p7→p3 (static features only). + If p47=True, transfers static p4-p7 (uv_x, uv_y, sin20_y, bias) to output channels. + + Input channel layout: [0-3: prev layer, 4-11: static (p0-p7)] + Static features: p0-p3 (RGB+D), p4 (uv_x), p5 (uv_y), p6 (sin20_y), p7 (bias) Binary format: Header (20 bytes): @@ -61,8 +64,10 @@ def generate_identity_weights(output_path, kernel_size=1, mip_level=0, mix=False if p47: # p47 mode: p4→ch0, p5→ch1, p6→ch2, p7→ch3 (static features only) + # Input channels: [0-3: prev layer, 4-11: static features (p0-p7)] + # p4-p7 are at input channels 8-11 for i in range(out_channels): - weights[i, i + 4, center, center] = 1.0 + weights[i, i + 8, center, center] = 1.0 elif mix: # Mix mode: 50-50 blend to avoid overflow for i in range(out_channels): |