Update README.md

README.md

@@ -4,4 +4,39 @@ metrics:
 - accuracy
 - f1
 ---
-See https://www.kaggle.com/code/dima806/headgear-image-detection-vit for more details.
+Returns headgear type given an image.
+
+See https://www.kaggle.com/code/dima806/headgear-image-detection-vit for more details.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6449300e3adf50d864095b90/Emppcn7eVbOL7r2YShjNX.png)
+
+```
+Classification report:
+
+                 precision    recall  f1-score   support
+
+          BERET     1.0000    0.9565    0.9778       115
+         FEDORA     0.9913    1.0000    0.9956       114
+        SOMBERO     1.0000    1.0000    1.0000       115
+       HARD HAT     1.0000    1.0000    1.0000       115
+            FEZ     1.0000    0.9912    0.9956       114
+      ZUCCHETTO     1.0000    0.9912    0.9956       114
+        TOP HAT     1.0000    1.0000    1.0000       115
+    DEERSTALKER     0.9913    1.0000    0.9956       114
+      ASCOT CAP     0.9500    1.0000    0.9744       114
+       PORK PIE     0.9739    0.9825    0.9782       114
+MILITARY HELMET     1.0000    1.0000    1.0000       115
+        BICORNE     1.0000    0.9912    0.9956       114
+FOOTBALL HELMET     1.0000    1.0000    1.0000       115
+     MOTARBOARD     0.9913    1.0000    0.9956       114
+         BOATER     1.0000    1.0000    1.0000       115
+    PITH HELMET     0.9913    1.0000    0.9956       114
+    SOUTHWESTER     1.0000    0.9912    0.9956       114
+         BOWLER     0.9912    0.9825    0.9868       114
+   GARRISON CAP     1.0000    0.9912    0.9956       114
+   BASEBALL CAP     1.0000    1.0000    1.0000       115
+
+       accuracy                         0.9939      2288
+      macro avg     0.9940    0.9939    0.9939      2288
+   weighted avg     0.9940    0.9939    0.9939      2288
+```