https://github.com/basicallysource/yolo-trainer
https://github.com/basicallysource/yolo-trainer
Last synced: about 1 month ago
JSON representation
- Host: GitHub
- URL: https://github.com/basicallysource/yolo-trainer
- Owner: basicallysource
- Created: 2026-01-16T21:28:12.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2026-01-17T00:23:53.000Z (6 months ago)
- Last Synced: 2026-01-17T12:54:27.575Z (6 months ago)
- Language: Python
- Size: 6.84 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# YOLO Segmentation Fine-tuning
## Config
Copy `config_classification_chamber_example.json` and edit paths:
```json
{
"data_yaml_path": "your_data.yaml",
"data_path": "/path/to/dataset",
"model_size": "small",
"epochs": 100,
"batch_size": 20,
"device": "cuda",
"val_split": 0.1
}
```
## Local Training
```bash
python finetune_segmenting.py config.json
```
## Remote Training
```bash
# on local
# this will sync the dataset and training code to the ssh'd gpu instance
python sync.py push config.json --remote user@host # sync code + data
# on the actual machine
python finetune_segmenting.py config.json
# on local
python sync.py pull config.json --remote user@host # pull checkpoints back
```
## Test
```bash
python test.py checkpoint.pt --webcam 0
```