https://github.com/khengyun/featurelayers

https://github.com/khengyun/featurelayers

ai keras-neural-networks keras-tensorflow python

Last synced: 22 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/khengyun/featurelayers
• Owner: khengyun
• Created: 2023-06-21T08:54:54.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-06-29T14:04:32.000Z (over 1 year ago)
• Last Synced: 2024-10-24T21:37:46.035Z (2 months ago)
• Topics: ai, keras-neural-networks, keras-tensorflow, python
• Language: Python
• Homepage: https://pypi.org/project/featurelayers/
• Size: 211 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# FeatureLayers

## Installation

```bash

pip install featurelayers

```

## Usage

### LBC Layers

```python

import numpy as np

from keras.models import Sequential

from keras.layers import Dense, Flatten

from featurelayers.layers.LBC import LBC

# Create a simple Keras model

model = Sequential()

# Add the LBC layer as the first layer in the model

model.add(LBC(filters=32, kernel_size=3, stride=1, padding='same', activation='relu', sparsity=0.9, name='lbc_layer'))

# Add a Flatten layer to convert the output to 1D

model.add(Flatten())

# Add a Dense layer for classification

model.add(Dense(units=10, activation='softmax'))

# Compile the model

model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

# Generate some dummy data

x_train = np.random.rand(100, 28, 28, 1)

y_train = np.random.randint(0, 10, size=(100,))

# Convert the labels to one-hot encoding

y_train = keras.utils.to_categorical(y_train, num_classes=10)

# Train the model

model.fit(x_train, y_train, epochs=10, batch_size=32)

```

__version__ = ""1.5.6""