https://github.com/gabrli/easycnn
EasyCNN it's liblary enabling quick creating, training and visualizing convolutional models (CNN).
https://github.com/gabrli/easycnn
ai cnn deep-learning easycnn keras model neural-network news opencv python tensorflow
Last synced: about 1 year ago
JSON representation
EasyCNN it's liblary enabling quick creating, training and visualizing convolutional models (CNN).
- Host: GitHub
- URL: https://github.com/gabrli/easycnn
- Owner: Gabrli
- License: mit
- Created: 2025-03-01T09:52:14.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-25T18:47:52.000Z (over 1 year ago)
- Last Synced: 2025-03-25T19:35:30.769Z (over 1 year ago)
- Topics: ai, cnn, deep-learning, easycnn, keras, model, neural-network, news, opencv, python, tensorflow
- Language: Python
- Homepage:
- Size: 1.19 MB
- Stars: 4
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Contributing: contributing.md
- License: LICENSE
Awesome Lists containing this project
README
# EasyCNN - Easy Creating and Visualizing CNN Model
EasyCNN it's liblary enabling quick creating, training and visualizing convolutional models (CNN).
## Features
- Easy definition of CNN layers
- Training and evolution models
- Visualization of the model structure
- 15 ready to easy and quick use the most popular presets of keras applications
## Documentation
[Documentation](https://github.com/Gabrli/EasyCNN---docs)
## Authors
- [@Gabrli](https://github.com/Gabrli)
## Tech Stack
**Languages:** Python
**Libraries:** Tensorflow, Matplotlib, Numpy, OpenCv
## License
[MIT](https://choosealicense.com/licenses/mit/)
## FAQ
#### what are the advantages ?
- Very easy and comfortable syntax
- Full control for developer
- Automatic data preparation and visualization processes
#### What functionalities are under construction?
- Presets for popular models
- Exporter and Converter for files with models
## Contributing
Contributions are always welcome!
See `contributing.md` for ways to get started.
Please adhere to this project's `code of conduct`.
## Usage/Examples
```python
from easycnn.core import EasyCNN
from easycnn.visualizer import TrainingVisualizer
import os
from tensorflow.keras.datasets import cifar10
class_names = ['car', 'plane', 'cat', 'dog', 'bird', 'deer', 'horse', 'frog', 'ship', 'truck']
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
my_file = os.path.join(os.path.dirname(__file__), 'car.jpg')
x_train = x_train[:2000]
y_train = y_train[:2000]
x_test = x_test[:400]
y_test = y_test[:400]
x_train = x_train / 255
x_test = x_test / 255
model = EasyCNN()
model.add_conv(32, 3)
model.add_max_pool(2)
model.add_conv(64, 3)
model.add_max_pool(2)
model.add_conv(128, 3)
model.add_max_pool(2)
model.add_flatten()
model.add_dense(10, activation='softmax')
model.compile()
history = model.train(x_train, y_train, x_test, y_test, epochs=5)
prediction = model.predict(my_file)
visualizer = TrainingVisualizer()
visualizer.plot_training(history)
```