DM-Diaz
/

VEDB-SimCLR-ResNet18-Periph

computer-vision

self-supervised-learning

egocentric-vision

visual-neuroscience

Model card Files Files and versions

DM-Diaz commited on 3 days ago

Commit

1c64afb

·

verified ·

1 Parent(s): 383532f

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -198,13 +198,13 @@ The four VEDB conditions used the same SimCLR architecture ([PyTorch-SimCLR](htt
 | Backbone | ResNet-18 |
 | Input size | `224 × 224` |
 | Epochs | 120 |
-| Batch size | 64 |
 | Optimizer | Adam |
-| Learning rate | `3 × 10^-4` |
 | Weight decay | `1 × 10^-4` |
 | Loss | NT-Xent |
 | Temperature (τ) | `0.07` |
-| Learning-rate schedule | Fixed |
 | Projection head | `Linear(512,512) → ReLU → Linear(512,128)` |
 | Mixed precision | FP16 |

 | Backbone | ResNet-18 |
 | Input size | `224 × 224` |
 | Epochs | 120 |
+| Batch size | 512 |
 | Optimizer | Adam |
+| Learning rate | `6 × 10^-4` |
 | Weight decay | `1 × 10^-4` |
 | Loss | NT-Xent |
 | Temperature (τ) | `0.07` |
+| Learning-rate schedule | CosineAnnealingLR (scheduler stepping begins after epoch 10) |
 | Projection head | `Linear(512,512) → ReLU → Linear(512,128)` |
 | Mixed precision | FP16 |