Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
metrics:
|
| 4 |
+
- accuracy
|
| 5 |
+
library_name: keras
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# Malaria Detection - Custom CNN Model
|
| 9 |
+
|
| 10 |
+
## Model Description
|
| 11 |
+
|
| 12 |
+
This is a custom Convolutional Neural Network (CNN) trained to detect malaria parasites in cell images. The model classifies blood cell images as either **Parasitized** or **Uninfected**.
|
| 13 |
+
|
| 14 |
+
## Model Architecture
|
| 15 |
+
|
| 16 |
+
- 3 Convolutional layers with ReLU activation
|
| 17 |
+
- MaxPooling layers for downsampling
|
| 18 |
+
- Dropout layer (0.5) for regularization
|
| 19 |
+
- Dense layers for classification
|
| 20 |
+
- Binary output with sigmoid activation
|
| 21 |
+
|
| 22 |
+
## Training Details
|
| 23 |
+
|
| 24 |
+
- **Dataset**: Cell Images for Detecting Malaria
|
| 25 |
+
- **Input Size**: 150x150x3
|
| 26 |
+
- **Optimizer**: Adam
|
| 27 |
+
- **Loss Function**: Binary Crossentropy
|
| 28 |
+
- **Epochs**: 10
|
| 29 |
+
- **Validation Split**: 20%
|
| 30 |
+
|
| 31 |
+
## Performance
|
| 32 |
+
|
| 33 |
+
- **Validation Accuracy**: {history.history['val_accuracy'][-1]:.4f}
|
| 34 |
+
- **Validation Loss**: {history.history['val_loss'][-1]:.4f}
|