| --- |
| title: Pokemon Object Detection (YOLOv8) |
| emoji: ⚡ |
| colorFrom: pink |
| colorTo: purple |
| sdk: gradio |
| sdk_version: "4.37.2" |
| app_file: app.py |
| pinned: false |
| --- |
| # Pokemon object detections |
| Using yolov8 after training with Google Colab |
| ## Dataset |
| Because of lack of data, there are only 7 classes: ```pikachu```, ```charmander```, ```bulbasaur```, ```squirtle```, ```eevee```, ```jigglypuff``` and ```other```. |
| |
|  |
| ## Requirements |
| ``` |
| pip install ultralytics |
| ``` |
| ## Preprocess Data |
| The ```convert.py``` used to convert *.xml* label file to *.txt* yolo label file. |
| Run ```resize_image.py``` to resize image's width to 640. |
| ## Train with Colab |
| Edit ```name.yaml```. |
| Upload images and labels. |
| ``` |
| !yolo train model=yolov8n.pt data=/content/name.yaml epochs=50 imgsz=640 |
| ``` |
| ## Training's Result |
| ```last.pt``` and ```best.pt``` in result folder. |
| |
|  |
| ## Predict |
| Run ```predict.py``` to see result. This is my predict to ```test.mp4```: |
| |
|  |
|
|
| #### Thank you for stopping by! |
|
|
