Downloads · 30 days
0
cvtechniques/Motherboard-Part-Locator
Motherboard-Part-Locator is a object detection model from cvtechniques. Use it when you need objects located in an image.
Downloads · 30 days
0
Access
Public
Updated Mar 19, 2026
Repo size
11.6 MB
Likes
0
Public
Click a slice to open those files.
.pt11 MB · 94%
From the Hugging Face model README
By Kamila Lopez-Avendano
This object detection model identifies ket parts of a motherboard. This fine-tuned in Yolov11n and is aimed to aid first-time pc builders in real time to give visual guidance when assembling their PC. The model uses Ultralytics and uses the nano variant for speed over accurarcy, enabling real-time inference so users can contiune their builds.
Architecture: Yolov11n (nano) Task: Object detection (boxes) Framework: Ultralytics
Forked From: GradResearch Computer Vision Model - https://universe.roboflow.com/gradresearch/gradresearch
Classes: 5 Images: 95
Dataset: Motherboard Part Locator (v5) - https://universe.roboflow.com/bis497/motherboard-part-locater
Classes: 4 Images (preaugmentation): 206 Images (post): 472
| Class Name |
|---|
| CPU Socket |
| PCIe Slot |
| Power Connector |
| RAM Slot |
| Class | Annotations |
|---|---|
| CPU Socket | 205 |
| PCIe Slot | 444 |
| Power Connector | 320 |
| RAM Slot | 221 |

Note: The dataset contained mixed detect/segment annotations inherited from the original fork. Only bounding box annotations were used during final training.
| Split | Images (pre-augmentation) | Split % |
|---|---|---|
| Train | 134 → 399 augmented | 65% |
| Validation | 49 | 24% |
| Test | 24 | 12% |
Augmentations (applied to expand dataset to 472 images):
Hardware: A100
Training time: ~0.07 hours
Platform: Google Colab
Epochs: 100
Patience: 50
| Metric | Score |
|---|---|
| Precision | 0.889 |
| Recall | 0.761 |
| mAP@50 | 0.827 |
| mAP@50-95 | 0.559 |
| Class | Precision | Recall | mAP@50 | mAP@50-95 |
|---|---|---|---|---|
| CPU Socket | 0.967 | 0.894 | 0.963 | 0.678 |
| PCIe Slot | 0.878 | 0.602 | 0.690 | 0.417 |
| Power Connector | 0.811 | 0.755 | 0.815 | 0.560 |
| RAM Slot | 0.899 | 0.792 | 0.839 | 0.592 |

| Metric | Original (Forked) | v5 (This Model) |
|---|---|---|
| Images | 195 (150/30/15) | 472 augmented |
| Split | 77/15/8% | 65/24/12% |
| mAP@50 | 91.9% | 82.7% |
| mAP@50-95 | N/A | 55.9% |
| Precision | 87.7% | 88.9% |
| Recall | 88.2% | 76.1% |
The lower mAP@50 compared to the original fork is expected. The success criteria set (mAP@50 > 75% and Precision > 60%) were met!