Table 2 Model training parameters.
Learning rate | Batch size | Epochs | Momentum | Weight_decay | Optimizer |
|---|---|---|---|---|---|
0.01 | 16 | 100 | 0.937 | 0.0005 | AdamW (iters ≤ 10k), SGD (iters > 10k) |
Learning rate | Batch size | Epochs | Momentum | Weight_decay | Optimizer |
|---|---|---|---|---|---|
0.01 | 16 | 100 | 0.937 | 0.0005 | AdamW (iters ≤ 10k), SGD (iters > 10k) |