Update README.md
Browse files
README.md
CHANGED
@@ -1,105 +0,0 @@
|
|
1 |
-
---
|
2 |
-
datasets:
|
3 |
-
- Illia56/Military-Aircraft-Detection
|
4 |
-
license: apache-2.0
|
5 |
-
metrics:
|
6 |
-
- accuracy
|
7 |
-
- f1
|
8 |
-
- recall
|
9 |
-
pipeline_tag: object-detection
|
10 |
-
---
|
11 |
-
|
12 |
-
# Model Card: Military Aircraft Detection with Vision Transformer (ViT)
|
13 |
-
|
14 |
-
## Model Information
|
15 |
-
|
16 |
-
- **Model Name:** Military Aircraft Image Detection
|
17 |
-
- **Model Type:** Vision Transformer (ViT)
|
18 |
-
|
19 |
-
|
20 |
-
## Model Overview
|
21 |
-
|
22 |
-
- **Purpose:** The model is designed for the detection and classification of military aircraft in images.
|
23 |
-
- **Intended Use:** Military surveillance, object recognition, and security applications.
|
24 |
-
|
25 |
-
## Model Training
|
26 |
-
|
27 |
-
- **Training Data:** Dataset of military aircraft images collected from Illia56/Military-Aircraft-Detection.
|
28 |
-
- **Data Preprocessing:** Random oversampling for class balance, data augmentation (rotation, flip, sharpness adjustment).
|
29 |
-
- **Model Architecture:** Vision Transformer (ViT) for image classification.
|
30 |
-
- **Pre-trained Model:** google/vit-base-patch16-224-in21k.
|
31 |
-
|
32 |
-
## Model Evaluation
|
33 |
-
|
34 |
-
- **Evaluation Metrics:**
|
35 |
-
- Accuracy
|
36 |
-
- F1 Score
|
37 |
-
- Confusion Matrix
|
38 |
-
- **Evaluation Dataset:** Split from the original dataset for testing.
|
39 |
-
- | Class | Precision | Recall | F1-Score | Support |
|
40 |
-
|------------|-----------|--------|----------|---------|
|
41 |
-
| A10 | 0.6716 | 0.7368 | 0.7027 | 247 |
|
42 |
-
| A400M | 0.6217 | 0.6748 | 0.6472 | 246 |
|
43 |
-
| AG600 | 0.4512 | 0.9919 | 0.6203 | 247 |
|
44 |
-
| AV8B | 0.6618 | 0.7287 | 0.6936 | 247 |
|
45 |
-
| B1 | 0.9000 | 0.6194 | 0.7338 | 247 |
|
46 |
-
| B2 | 0.7862 | 0.9231 | 0.8492 | 247 |
|
47 |
-
| B52 | 0.9528 | 0.4089 | 0.5722 | 247 |
|
48 |
-
| Be200 | 0.8333 | 0.8300 | 0.8316 | 247 |
|
49 |
-
| C130 | 0.8600 | 0.1748 | 0.2905 | 246 |
|
50 |
-
| C17 | 0.5556 | 0.0405 | 0.0755 | 247 |
|
51 |
-
| C2 | 0.5845 | 0.8543 | 0.6941 | 247 |
|
52 |
-
| C5 | 0.3776 | 0.7490 | 0.5020 | 247 |
|
53 |
-
| E2 | 0.8447 | 0.9028 | 0.8728 | 247 |
|
54 |
-
| E7 | 0.6000 | 0.9595 | 0.7383 | 247 |
|
55 |
-
| EF2000 | 1.0000 | 0.0364 | 0.0703 | 247 |
|
56 |
-
| F117 | 0.6005 | 0.9433 | 0.7339 | 247 |
|
57 |
-
| F14 | 0.9773 | 0.1741 | 0.2955 | 247 |
|
58 |
-
| F15 | 0.2919 | 0.2186 | 0.2500 | 247 |
|
59 |
-
| F16 | 0.8333 | 0.0203 | 0.0397 | 246 |
|
60 |
-
| F18 | 0.9355 | 0.2348 | 0.3754 | 247 |
|
61 |
-
| F22 | 0.4624 | 0.4980 | 0.4795 | 247 |
|
62 |
-
| F35 | 0.5373 | 0.2915 | 0.3780 | 247 |
|
63 |
-
| F4 | 0.4317 | 0.2429 | 0.3109 | 247 |
|
64 |
-
| J10 | 0.8711 | 0.6842 | 0.7664 | 247 |
|
65 |
-
| J20 | 0.5049 | 0.6301 | 0.5606 | 246 |
|
66 |
-
| JAS39 | 0.4535 | 0.4737 | 0.4634 | 247 |
|
67 |
-
| KC135 | 0.8957 | 0.7683 | 0.8271 | 246 |
|
68 |
-
| MQ9 | 0.7358 | 0.8943 | 0.8073 | 246 |
|
69 |
-
| Mig31 | 0.6080 | 0.4899 | 0.5426 | 247 |
|
70 |
-
| Mirage2000 | 0.3245 | 0.6478 | 0.4324 | 247 |
|
71 |
-
| P3 | 0.9423 | 0.3968 | 0.5584 | 247 |
|
72 |
-
| RQ4 | 0.7166 | 0.8907 | 0.7942 | 247 |
|
73 |
-
| Rafale | 0.3063 | 0.3968 | 0.3457 | 247 |
|
74 |
-
| SR71 | 0.7824 | 0.7571 | 0.7695 | 247 |
|
75 |
-
| Su25 | 1.0000 | 0.3618 | 0.5313 | 246 |
|
76 |
-
| Su34 | 0.5340 | 0.8583 | 0.6584 | 247 |
|
77 |
-
| Su57 | 0.6143 | 0.7317 | 0.6679 | 246 |
|
78 |
-
| Tornado | 0.6883 | 0.2146 | 0.3272 | 247 |
|
79 |
-
| Tu160 | 0.8000 | 0.8421 | 0.8205 | 247 |
|
80 |
-
| Tu95 | 0.8340 | 0.8543 | 0.8440 | 247 |
|
81 |
-
| U2 | 0.9371 | 0.6032 | 0.7340 | 247 |
|
82 |
-
| US2 | 0.7074 | 0.6559 | 0.6807 | 247 |
|
83 |
-
| V22 | 0.7212 | 0.9109 | 0.8050 | 247 |
|
84 |
-
| Vulcan | 0.3343 | 0.8947 | 0.4868 | 247 |
|
85 |
-
| XB70 | 0.6657 | 0.9676 | 0.7888 | 247 |
|
86 |
-
| YF23 | 0.5490 | 0.7967 | 0.6501 | 246 |
|
87 |
-
| Accuracy | | | 0.6082 | 11353 |
|
88 |
-
| Macro Avg | 0.6804 | 0.6082 | 0.5787 | 11353 |
|
89 |
-
| Weighted Avg| 0.6803 | 0.6082 | 0.5787 | 11353 |
|
90 |
-
|
91 |
-
## Potential Bias
|
92 |
-
|
93 |
-
- **Bias in Training Data:** Possible biases related to the data collection process.
|
94 |
-
- **Limitations:** Potential biases due to the nature of the dataset and model architecture.
|
95 |
-
|
96 |
-
## Ethical Considerations
|
97 |
-
|
98 |
-
- **Fairness:** Address any concerns regarding fairness and potential bias in model predictions.
|
99 |
-
- **Privacy:** Describe any privacy considerations related to the model's deployment and use.
|
100 |
-
|
101 |
-
## Model Usage Guidelines
|
102 |
-
|
103 |
-
- **Recommended Use Cases:** Military surveillance, security applications.
|
104 |
-
- **Limitations:** Clearly outline model limitations and potential failure scenarios.
|
105 |
-
- **Legal and Ethical Considerations:** Compliance with legal and ethical standards.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|