Update README.md

README.md

@@ -14,7 +14,6 @@ language:
 metrics:
 - mae
 ---
-
 # Model Card for MNIST Eraser Repair U-Net
 
 This is a PyTorch-based U-Net Autoencoder designed to reconstruct partially erased handwritten digits from the MNIST dataset. It was created as a submission for the Slovak AI Olympics 2025/26.
@@ -59,7 +58,7 @@ Because the task required pairs of (damaged, clean) images, a synthetic damage g
 - **Learning Rate:** 1e-3
 - **Loss Function:** L1 Loss (Mean Absolute Error - MAE). MAE was chosen over MSE to encourage sharper edges and reduce sensitivity to outliers.
 - **Epochs:** 16
-- **Hardware Setup:** Trained using a T4 GPU via Google Colab.
+- **Hardware Setup:** Trained using a GPU via Google Colab.
 
 ## Evaluation
 
@@ -69,4 +68,20 @@ The model was evaluated using a challenge test set of 2,000 erased digits. The p
 ### Results
 - The model successfully learned to infer missing segments of characters by utilizing the surrounding context. 
 - Visual inspection confirms strong qualitative performance; the model restores digits plausibly even when major loops or structural lines are missing.
-- Most reconstruction errors are highly localized and low in magnitude (as shown by the very concentrated, low-error distribution in the training records).
+- Most reconstruction errors are highly localized and low in magnitude (as shown by the very concentrated, low-error distribution in the training records).
+
+#### Visual Performance
+
+![Model Result](https://raw.githubusercontent.com/mrtineu/fix-erased-numbers/main/images/output.png)
+*Top: Input (Rubbered), Middle: Output (Fixed), Bottom: Ground Truth*
+
+![Task Result](https://raw.githubusercontent.com/mrtineu/fix-erased-numbers/main/images/task_output.png)
+*Top: Input (Rubbered), Bottom: Output (Fixed) from the challenge dataset*
+
+#### Performance Charts
+
+![Training Loss](https://raw.githubusercontent.com/mrtineu/fix-erased-numbers/main/images/training_loss.png)
+*Shows the decrease in L1 Loss over 16 epochs.*
+
+![Error Distribution](https://raw.githubusercontent.com/mrtineu/fix-erased-numbers/main/images/error_distribution.png)
+*Histogram of the L1 Loss on the test set, showing most errors are very low.*