Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Model Card for aedupuga/image-autogluon-predictor
|
| 2 |
+
|
| 3 |
+
### Model Description
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
This is an AutoGluon Image AutoML NN implementation on a image dataset containing cover images of books. The model predicts whether the book is "fiction" or "non-fiction".
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- **Model developed by:** Anuhya Edupuganti
|
| 10 |
+
- **Model type:** AutoGluon TabularPredictor
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
### Model Sources [optional]
|
| 14 |
+
|
| 15 |
+
<!-- Provide the basic links for the model. -->
|
| 16 |
+
- **Dataset:** jennifee/HW1-images-dataset
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
### Direct Use
|
| 20 |
+
- This model was intended to practice automl implementation on an image dataset
|
| 21 |
+
|
| 22 |
+
## Bias, Risks, and Limitations
|
| 23 |
+
- Small data size. cannot to generallised to all existing books on the market.
|
| 24 |
+
-
|
| 25 |
+
## Training Data:
|
| 26 |
+
|
| 27 |
+
The model was trained on the augmented split of the "jennifee/HW1-images-dataset".
|
| 28 |
+
|
| 29 |
+
## Evaluation Data:
|
| 30 |
+
|
| 31 |
+
The model achieved an accuracy of 1.000 and a weighted F1 score of 1.000 on the original dataset.
|
| 32 |
+
|
| 33 |
+
## Model Card Contact
|
| 34 |
+
|
| 35 |
+
Anuhya Edupuganti (Carnegie Mellon Univerity)- aedupuga@andrew.cmu.edu
|