diff options
Diffstat (limited to 'BASELINES.md')
| -rw-r--r-- | BASELINES.md | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/BASELINES.md b/BASELINES.md index 34e9f58..cfdb3f5 100644 --- a/BASELINES.md +++ b/BASELINES.md @@ -57,7 +57,10 @@ model.Q.mode=sym_Y The inherited configuration supplies three convolutional layers plus a 1500-unit fully connected layer, batch size 32, 400 epochs, label smoothing 0.05, SGD momentum 0.9, weight decay `1e-4`, two warmup epochs and cosine -decay. Y and Q use learning rate `0.001`. The paper reports +decay. The resolved author config uses softmax outputs with MSE loss; Y and Q +use learning rate `0.001`. The current author loop interprets `n_epochs=400` +as an epoch-0 evaluation followed by 399 optimization epochs, and the audit +records both counts rather than silently relabelling them. The paper reports `17.03 ± 0.21%` top-1 error (`82.97 ± 0.21%` accuracy) for symmetric-plastic BurstCCN. |