Update README.md
Browse files
README.md
CHANGED
|
@@ -8,4 +8,49 @@ pipeline_tag: image-classification
|
|
| 8 |
tags:
|
| 9 |
- aircraft
|
| 10 |
- airplane
|
| 11 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
tags:
|
| 9 |
- aircraft
|
| 10 |
- airplane
|
| 11 |
+
---
|
| 12 |
+
# Aircraft Classifier
|
| 13 |
+
|
| 14 |
+
This repository contains a pre-trained PyTorch model for classifying aircraft types based on images. The model file `aircraft_classifier.pth` can be downloaded and used to classify images of various aircraft models.
|
| 15 |
+
|
| 16 |
+
## Model Overview
|
| 17 |
+
|
| 18 |
+
The `aircraft_classifier.pth` file is a PyTorch model trained on a dataset of aircraft images. It achieves a test accuracy of **75.26%** on the FGVC Aircraft test dataset, making it a reliable choice for identifying aircraft types. The model is designed to be lightweight and efficient for real-time applications.
|
| 19 |
+
|
| 20 |
+
## Requirements
|
| 21 |
+
|
| 22 |
+
- **Python** 3.7 or higher
|
| 23 |
+
- **PyTorch** 1.8 or higher
|
| 24 |
+
- **torchvision** (for loading and preprocessing images)
|
| 25 |
+
|
| 26 |
+
## Usage
|
| 27 |
+
|
| 28 |
+
1. Clone this repository and install dependencies.
|
| 29 |
+
```bash
|
| 30 |
+
git clone <repository-url>
|
| 31 |
+
cd <repository-folder>
|
| 32 |
+
pip install torch torchvision
|
| 33 |
+
```
|
| 34 |
+
2. Load and use the model in your Python script:
|
| 35 |
+
```python
|
| 36 |
+
import torch
|
| 37 |
+
from torchvision import transforms
|
| 38 |
+
from PIL import Image
|
| 39 |
+
|
| 40 |
+
# Load the model
|
| 41 |
+
model = torch.load('aircraft_classifier.pth')
|
| 42 |
+
model.eval() # Set to evaluation mode
|
| 43 |
+
|
| 44 |
+
# Load and preprocess the image
|
| 45 |
+
transform = transforms.Compose([
|
| 46 |
+
transforms.Resize((224, 224)),
|
| 47 |
+
transforms.ToTensor(),
|
| 48 |
+
])
|
| 49 |
+
img = Image.open('path_to_image.jpg')
|
| 50 |
+
img = transform(img).view(1, 3, 224, 224) # Reshape to (1, 3, 224, 224) for batch processing
|
| 51 |
+
|
| 52 |
+
# Predict
|
| 53 |
+
with torch.no_grad():
|
| 54 |
+
output = model(img)
|
| 55 |
+
_, predicted = torch.max(output, 1)
|
| 56 |
+
print("Predicted Aircraft Type:", predicted.item())
|