avinashhm/welding-defect-yolov8-full-training
By avinashhm · ↓ 9 · ♥ 0 · Updated 2025-06-02
What's in this repo
This page lists the files in avinashhm/welding-defect-yolov8-full-training, including best.onnx.
- 1 ONNX models (.onnx files)
- 28 files, including 14 .jpg, 7 .png, 2 .pt, 1 .md, 1 .yaml, 1 .csv
- Last updated 2025-06-02
ONNX files
| File | Size | Download |
|---|---|---|
| weights/best.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
library_name: ultralytics tags:
- object-detection
- yolov8
- welding-defect
- industrial-inspection
Welding Defect Detection Model (YOLOv8)
This is a fine-tuned YOLOv8 model for detecting welding defects such as:
- Good Weld
- Bad Weld
- Defect
Includes full training artifacts:
- Best model weights (
best.pt) - Final model weights (
last.pt) - Training logs
- Validation predictions
- Augmented training batches
Training Details
- Model Type: YOLOv8
- Dataset: The Welding Defect Dataset - v2
- Classes: 3
- Epochs: 100
- Image Size: 640x640
- Batch Size: 16
Usage
from ultralytics import YOLO
model = YOLO("YOUR_HF_USERNAME/welding-defect-yolov8-full-training")
results = model("image.jpg")
results[0].show()
Model info
object-detection
ultralytics
ultralytics
onnx
object-detection
yolov8
welding-defect
industrial-inspection
region:us
↓ 9
♥ 0
Created: 2025-06-02
Updated: 2025-06-02
View on Hugging FaceFiles (28)
.gitattributes
F1_curve.png
PR_curve.png
P_curve.png
README.md
R_curve.png
args.yaml
confusion_matrix.png
confusion_matrix_normalized.png
labels.jpg
labels_correlogram.jpg
results.csv
results.png
train_batch0.jpg
train_batch1.jpg
train_batch2.jpg
train_batch9180.jpg
train_batch9181.jpg
train_batch9182.jpg
val_batch0_labels.jpg
val_batch0_pred.jpg
val_batch1_labels.jpg
val_batch1_pred.jpg
val_batch2_labels.jpg
val_batch2_pred.jpg
weights/best.onnx
ONNX
weights/best.pt
weights/last.pt