diff options
| -rw-r--r-- | doc/CNN_V2_DEBUG_TOOLS.md | 4 | ||||
| -rwxr-xr-x | training/gen_identity_weights.py | 22 |
2 files changed, 13 insertions, 13 deletions
diff --git a/doc/CNN_V2_DEBUG_TOOLS.md b/doc/CNN_V2_DEBUG_TOOLS.md index dfea63e..8d1289a 100644 --- a/doc/CNN_V2_DEBUG_TOOLS.md +++ b/doc/CNN_V2_DEBUG_TOOLS.md @@ -18,7 +18,7 @@ Tools for investigating CNN v2 mismatch between HTML tool and cnn_test. # 3×3 identity ./training/gen_identity_weights.py workspaces/main/weights/cnn_v2_identity_3x3.bin --kernel-size 3 -# Mix mode: p0+p4, p1+p5, p2+p6, p3+p7 +# Mix mode: 50-50 blend (0.5*p0+0.5*p4, etc) ./training/gen_identity_weights.py output.bin --mix # Static features only: p4→ch0, p5→ch1, p6→ch2, p7→ch3 @@ -31,7 +31,7 @@ Tools for investigating CNN v2 mismatch between HTML tool and cnn_test. **Output:** - Single layer, 12D→4D (4 input channels + 8 static features) - Identity mode: Output Ch{0,1,2,3} = Input Ch{0,1,2,3} -- Mix mode (--mix): Output Ch{i} = Input Ch{i} + Input Ch{i+4} (blends input with static features) +- Mix mode (--mix): Output Ch{i} = 0.5*Input Ch{i} + 0.5*Input Ch{i+4} (50-50 blend, avoids overflow) - Static mode (--p47): Output Ch{i} = Input Ch{i+4} (static features only, visualizes p4-p7) - Minimal file size (~136 bytes for 1×1, ~904 bytes for 3×3) diff --git a/training/gen_identity_weights.py b/training/gen_identity_weights.py index 0d79593..5756e67 100755 --- a/training/gen_identity_weights.py +++ b/training/gen_identity_weights.py @@ -4,8 +4,8 @@ Creates trivial .bin with 1 layer, 1×1 kernel, identity passthrough. Output Ch{0,1,2,3} = Input Ch{0,1,2,3} (ignores static features). -With --mix: Output Ch{i} = Input Ch{i} + Input Ch{i+4} - (p0+p4, p1+p5, p2+p6, p3+p7) +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) @@ -25,7 +25,7 @@ from pathlib import Path def generate_identity_weights(output_path, kernel_size=1, mip_level=0, mix=False, p47=False): """Generate identity weights: output = input (ignores static features). - If mix=True, adds p4→p0, p5→p1, p6→p2, p7→p3 (blends input with static). + 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). Binary format: @@ -63,16 +63,16 @@ def generate_identity_weights(output_path, kernel_size=1, mip_level=0, mix=False # p47 mode: p4→ch0, p5→ch1, p6→ch2, p7→ch3 (static features only) for i in range(out_channels): weights[i, i + 4, center, center] = 1.0 + elif mix: + # Mix mode: 50-50 blend to avoid overflow + for i in range(out_channels): + weights[i, i, center, center] = 0.5 # 0.5*p{i} + weights[i, i + 4, center, center] = 0.5 # 0.5*p{i+4} else: - # Set diagonal to 1.0 (output ch i = input ch i) + # Identity: output ch i = input ch i for i in range(out_channels): weights[i, i, center, center] = 1.0 - # If mix, add p4→p0, p5→p1, p6→p2, p7→p3 - if mix: - for i in range(out_channels): - weights[i, i + 4, center, center] = 1.0 - # Flatten weights_flat = weights.flatten() weight_count = len(weights_flat) @@ -84,7 +84,7 @@ def generate_identity_weights(output_path, kernel_size=1, mip_level=0, mix=False print(f" Weights: {weight_count}") print(f" Mip level: {mip_level}") if mix: - print(f" Mode: p0+p4, p1+p5, p2+p6, p3+p7") + print(f" Mode: 0.5*p0+0.5*p4, 0.5*p1+0.5*p5, 0.5*p2+0.5*p6, 0.5*p3+0.5*p7") elif p47: print(f" Mode: p4→ch0, p5→ch1, p6→ch2, p7→ch3") @@ -150,7 +150,7 @@ def main(): parser.add_argument('--mip-level', type=int, default=0, help='Mip level for p0-p3 features (default: 0)') parser.add_argument('--mix', action='store_true', - help='Mix mode: p0+p4, p1+p5, p2+p6, p3+p7') + help='Mix mode: 50-50 blend of p0-p3 and p4-p7') parser.add_argument('--p47', action='store_true', help='Static features only: p4→ch0, p5→ch1, p6→ch2, p7→ch3') |