Instructions to use DevBhuyan/Digit-Recognition-Lightweight with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use DevBhuyan/Digit-Recognition-Lightweight with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://DevBhuyan/Digit-Recognition-Lightweight") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,4 +5,6 @@ language:
|
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
| 7 |
pipeline_tag: image-classification
|
| 8 |
-
---
|
|
|
|
|
|
|
|
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
| 7 |
pipeline_tag: image-classification
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
An ultra-lightweight model useful for distinguishing between different handwritten digits. All in less than 1.8 MiB, and gives a validation accuracy of 98.60% on Kaggle's private testing dataset.
|