Instructions to use DataScienceProject/CNN_And_ELA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use DataScienceProject/CNN_And_ELA with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://DataScienceProject/CNN_And_ELA") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -76,10 +76,15 @@ Train the CNN with the Preprocessed images , use valitadion set.
|
|
| 76 |
|
| 77 |
|
| 78 |
-optimizer = RMSprop(lr=0.0005, rho=0.9, epsilon=1e-08, decay=0.0)
|
|
|
|
| 79 |
-epochs = 22
|
|
|
|
| 80 |
-batch_size = 100
|
|
|
|
| 81 |
-loss = "categorical_crossentropy"
|
|
|
|
| 82 |
-metrics=["accuracy"]
|
|
|
|
| 83 |
-early_stopping = EarlyStopping(monitor='val_acc',min_delta=0,patience=2,verbose=0, mode='auto')
|
| 84 |
|
| 85 |
|
|
|
|
| 76 |
|
| 77 |
|
| 78 |
-optimizer = RMSprop(lr=0.0005, rho=0.9, epsilon=1e-08, decay=0.0)
|
| 79 |
+
|
| 80 |
-epochs = 22
|
| 81 |
+
|
| 82 |
-batch_size = 100
|
| 83 |
+
|
| 84 |
-loss = "categorical_crossentropy"
|
| 85 |
+
|
| 86 |
-metrics=["accuracy"]
|
| 87 |
+
|
| 88 |
-early_stopping = EarlyStopping(monitor='val_acc',min_delta=0,patience=2,verbose=0, mode='auto')
|
| 89 |
|
| 90 |
|