Update README.md
Browse files
README.md
CHANGED
|
@@ -1,30 +1,33 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
|
|
|
|
|
|
| 3 |
datasets:
|
| 4 |
-
- benediktkol/DDOS
|
| 5 |
metrics:
|
| 6 |
-
- accuracy
|
|
|
|
| 7 |
|
| 8 |
-
YOLO298B is a custom‑trained Ultralytics YOLO model (`best.pt`) built by **Team
|
| 9 |
It detects aerial classes in aerial imagery collected by autonomous drones.
|
| 10 |
|
| 11 |
-
| Attribute
|
| 12 |
-
|
| 13 |
-
| **Architecture** | YOLO‑v9‑S
|
| 14 |
-
| **Input size** | 640 × 640
|
| 15 |
-
| **Classes** | *n*
|
| 16 |
-
| **Checkpoint** | 5.5
|
| 17 |
|
| 18 |
## Intended uses & limitations
|
| 19 |
|
| 20 |
-
| Use‑case
|
| 21 |
-
|
| 22 |
-
| Real‑time obstacle detection on UAVs
|
| 23 |
-
| Academic research / benchmarking
|
| 24 |
-
| Safety‑critical deployment w/o human
|
| 25 |
|
| 26 |
## Training data
|
| 27 |
-
Dataset:
|
| 28 |
Split: 80 % train · 10 % val · 10 % test
|
| 29 |
|
| 30 |
## Quick start
|
|
@@ -34,4 +37,4 @@ from ultralytics import YOLO
|
|
| 34 |
|
| 35 |
model = YOLO("vsham001/Yolo298B")
|
| 36 |
results = model("https://ultralytics.com/images/bus.jpg")
|
| 37 |
-
results[0].show()
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0 # must match Settings → Licensing
|
| 3 |
+
pipeline_tag: object-detection
|
| 4 |
+
model_type: yolov9
|
| 5 |
datasets:
|
| 6 |
+
- benediktkol/DDOS
|
| 7 |
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
---
|
| 10 |
|
| 11 |
+
YOLO298B is a custom‑trained Ultralytics YOLO model (`best.pt`) built by **Team 6 (SJSU)**.
|
| 12 |
It detects aerial classes in aerial imagery collected by autonomous drones.
|
| 13 |
|
| 14 |
+
| Attribute | Value |
|
| 15 |
+
|------------------|----------------|
|
| 16 |
+
| **Architecture** | YOLO‑v9‑S |
|
| 17 |
+
| **Input size** | 640 × 640 px |
|
| 18 |
+
| **Classes** | *n* |
|
| 19 |
+
| **Checkpoint** | 5.5 MB |
|
| 20 |
|
| 21 |
## Intended uses & limitations
|
| 22 |
|
| 23 |
+
| Use‑case | ✅ Recommended | 🚫 Not recommended |
|
| 24 |
+
|--------------------------------------|---------------|--------------------|
|
| 25 |
+
| Real‑time obstacle detection on UAVs | ✔️ | |
|
| 26 |
+
| Academic research / benchmarking | ✔️ | |
|
| 27 |
+
| Safety‑critical deployment w/o human | | ❌ |
|
| 28 |
|
| 29 |
## Training data
|
| 30 |
+
Dataset: **benediktkol/DDOS** – contains drone‑view images with obstacles (*\<brief description\>*).
|
| 31 |
Split: 80 % train · 10 % val · 10 % test
|
| 32 |
|
| 33 |
## Quick start
|
|
|
|
| 37 |
|
| 38 |
model = YOLO("vsham001/Yolo298B")
|
| 39 |
results = model("https://ultralytics.com/images/bus.jpg")
|
| 40 |
+
results[0].show()
|