|
--- |
|
license: mit |
|
datasets: |
|
- cifar10 |
|
library_name: keras |
|
pipeline_tag: image-classification |
|
--- |
|
### Model Name: `Enhanced-CIFAR10-CNN` |
|
|
|
**Description:** |
|
|
|
Introducing `Enhanced-CIFAR10-CNN`, a state-of-the-art Convolutional Neural Network (CNN) trained on the CIFAR dataset. Based on extensive research, with an impressive accuracy of 89%, this model sets a new benchmark in image classification tasks. What sets it apart? |
|
|
|
- **High Performance**: Achieves an accuracy rate of 86%, surpassing standard benchmarks. |
|
|
|
- **Fast Inference**: Optimized for speed, this model ensures quick predictions without compromising on accuracy. |
|
|
|
- **Compact Size**: Its small footprint makes it ideal for edge deployments and integration into existing systems. |
|
|
|
- **Transfer Learning Ready**: The model's architecture and pre-trained weights make it an excellent candidate for fine-tuning and further development in various applications. |
|
|
|
**Usage Examples:** |
|
|
|
```python |
|
from keras.models import load_model |
|
|
|
# Load the model |
|
model = load_model('path/to/enhancedCIFAR-10-CNN.h5') |
|
|
|
# Perform inference |
|
result = model.predict(input_data) |
|
``` |
|
|
|
**Dependencies:** |
|
|
|
- Keras >= 2.4.0 |
|
- TensorFlow >= 2.5.0 |
|
|
|
**Citation:** |
|
Ogundokun, Roseline Oluwaseun, et al. "Improved CNN based on batch normalization and adam optimizer." International Conference on Computational Science and Its Applications. Cham: Springer International Publishing, 2022. |
|
If you find this model useful, please cite our work. |
