Instructions to use keras-io/SimSiam with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TF-Keras
How to use keras-io/SimSiam 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/SimSiam") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,9 +14,10 @@ The trained model can be used as a learned representation for downstream tasks l
|
|
| 14 |
## Training and evaluation data
|
| 15 |
|
| 16 |
Original Cifar 10 train & test dataset were loaded from tensorflow datasets.
|
|
|
|
| 17 |
Two particular augmentation transforms that seem to matter the most are:
|
| 18 |
-
|
| 19 |
-
|
| 20 |
|
| 21 |
## Training procedure
|
| 22 |
|
|
|
|
| 14 |
## Training and evaluation data
|
| 15 |
|
| 16 |
Original Cifar 10 train & test dataset were loaded from tensorflow datasets.
|
| 17 |
+
|
| 18 |
Two particular augmentation transforms that seem to matter the most are:
|
| 19 |
+
- Random resized crops
|
| 20 |
+
- Color distortions
|
| 21 |
|
| 22 |
## Training procedure
|
| 23 |
|