Instructions to use keras-io/CutMix_data_augmentation_for_image_classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TF-Keras
How to use keras-io/CutMix_data_augmentation_for_image_classification with TF-Keras:
# Note: 'keras<3.x' or 'tf_keras' must be installed (legacy) # See https://github.com/keras-team/tf-keras for more details. from huggingface_hub import from_pretrained_keras model = from_pretrained_keras("keras-io/CutMix_data_augmentation_for_image_classification") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse filesadded details about the metrics
README.md
CHANGED
|
@@ -31,7 +31,9 @@ The following hyperparameters were used during training:
|
|
| 31 |
- training_precision: float32
|
| 32 |
|
| 33 |
## Training Metrics
|
| 34 |
-
|
|
|
|
|
|
|
| 35 |
## Model Plot
|
| 36 |
|
| 37 |
<details>
|
|
|
|
| 31 |
- training_precision: float32
|
| 32 |
|
| 33 |
## Training Metrics
|
| 34 |
+
After 20 Epocs, the accuracy of the model trained on the CutMix augmented data is 79.61%, while the accuracy of the model trained on the original data is 75.62%. I also found that the training on the original data was slightly faster.
|
| 35 |
+
|
| 36 |
+
|
| 37 |
## Model Plot
|
| 38 |
|
| 39 |
<details>
|