speedblitz commited on
Commit
bbe8be7
·
verified ·
1 Parent(s): b22b7dd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -13,3 +13,8 @@ This repository contains the trained weights and architecture for a Hybrid Atten
13
  * `hat_phase2.pth`: The final fine-tuned PyTorch model weights.
14
  * `hat_arch.py`: The architecture definition used to instantiate the model.
15
  * `config.json`: The exact hyperparameters required to construct the architecture.
 
 
 
 
 
 
13
  * `hat_phase2.pth`: The final fine-tuned PyTorch model weights.
14
  * `hat_arch.py`: The architecture definition used to instantiate the model.
15
  * `config.json`: The exact hyperparameters required to construct the architecture.
16
+
17
+ ## Evaluation
18
+ **Note on Reproducibility:** The reported PSNR of 39.57 is achieved using **8-fold Test-Time Augmentation (TTA)** combined with overlapping patch inference (tile size 128) to prevent memory constraints.
19
+
20
+ Running a single raw forward pass without TTA will result in a slightly lower PSNR. Please refer to the provided inference script/notebook for the exact TTA implementation.