Update README.md
Browse files
README.md
CHANGED
|
@@ -16,4 +16,22 @@ datasets:
|
|
| 16 |
metrics:
|
| 17 |
- accuracy
|
| 18 |
- f1
|
| 19 |
-
library_name: autogluon
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
metrics:
|
| 17 |
- accuracy
|
| 18 |
- f1
|
| 19 |
+
library_name: autogluon
|
| 20 |
+
|
| 21 |
+
Training Details:
|
| 22 |
+
-The model was trained using AutoGluon's MultiModalPredictor with the following configuration:
|
| 23 |
+
|
| 24 |
+
-Problem Type: Classification
|
| 25 |
+
-Evaluation Metric: Accuracy
|
| 26 |
+
-Presets: medium_quality
|
| 27 |
+
-Hyperparameters:
|
| 28 |
+
-model.names: ["timm_image"]
|
| 29 |
+
-model.timm_image.checkpoint_name: "resnet18"
|
| 30 |
+
-The training data used was the 'augmented' split of the dataset, with a 80/20 train/test split for tuning.
|
| 31 |
+
|
| 32 |
+
Evaluation:
|
| 33 |
+
-The model was evaluated on the 'original' split of the dataset.
|
| 34 |
+
|
| 35 |
+
-Accuracy: 1.0000
|
| 36 |
+
-Weighted F1: 1.0000
|
| 37 |
+
-Note: These results are based on the evaluation performed in the provided Colab notebook.
|