Image Classification
Keras
biologically-inspired
neuromorphic
dendritic-computing
green-ai
small-parameters-footprint
Eval Results (legacy)
Instructions to use febrifahmi/NoD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use febrifahmi/NoD with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://febrifahmi/NoD") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -68,7 +68,7 @@ This model is a custom-designed architecture developed independently. It is not
|
|
| 68 |
## Usage
|
| 69 |
|
| 70 |
## Create NoDClassificationLayer class
|
| 71 |
-
```
|
| 72 |
import tensorflow as tf
|
| 73 |
from tensorflow.keras import layers, Model, initializers, datasets
|
| 74 |
from tensorflow.keras.models import load_model
|
|
@@ -197,7 +197,7 @@ class NoDClassificationLayer(layers.Layer):
|
|
| 197 |
```
|
| 198 |
## Create the load balaced layer class
|
| 199 |
|
| 200 |
-
```
|
| 201 |
import tensorflow as tf
|
| 202 |
from tensorflow.keras import layers
|
| 203 |
|
|
@@ -275,7 +275,7 @@ class BalancedNoDClassificationLayer(layers.Layer):
|
|
| 275 |
|
| 276 |
## Load and evaluate saved model
|
| 277 |
|
| 278 |
-
```
|
| 279 |
def evaluate_saved_model(model_path):
|
| 280 |
print(f"[INFO] Loading model from '{model_path}'...")
|
| 281 |
|
|
|
|
| 68 |
## Usage
|
| 69 |
|
| 70 |
## Create NoDClassificationLayer class
|
| 71 |
+
```python
|
| 72 |
import tensorflow as tf
|
| 73 |
from tensorflow.keras import layers, Model, initializers, datasets
|
| 74 |
from tensorflow.keras.models import load_model
|
|
|
|
| 197 |
```
|
| 198 |
## Create the load balaced layer class
|
| 199 |
|
| 200 |
+
```python
|
| 201 |
import tensorflow as tf
|
| 202 |
from tensorflow.keras import layers
|
| 203 |
|
|
|
|
| 275 |
|
| 276 |
## Load and evaluate saved model
|
| 277 |
|
| 278 |
+
```python
|
| 279 |
def evaluate_saved_model(model_path):
|
| 280 |
print(f"[INFO] Loading model from '{model_path}'...")
|
| 281 |
|