Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
This repository contains the fine-tuning script and weights of YOLOv10m on links dataset.
|
3 |
+
|
4 |
+
### The links dataset :
|
5 |
+
- The dataset contains about 50000 images (some corrupt images were removed).
|
6 |
+
|
7 |
+
### The training :
|
8 |
+
- We fine-tuned YOLOv10m with this configuration :
|
9 |
+
Model: yolov10m.pt
|
10 |
+
|
11 |
+
Epochs: 10
|
12 |
+
|
13 |
+
Batch: 66
|
14 |
+
|
15 |
+
device: [0,1,2,3,4,5] (GPU L4 x 6)
|
16 |
+
|
17 |
+
size :
|
18 |
+
|
19 |
+
- Training time :
|
20 |
+
|
21 |
+
### The results :
|
22 |
+
|
23 |
+
##### Confusion matrix :
|
24 |
+
|
25 |
+
##### Training loss :
|
26 |
+
|
27 |
+
##### Precision, F1 and recall :
|