Developer Guide
Complete guide to setting up development environment and contributing
🛠️ Development Setup
1 Clone
git clone https://github.com/Purushothaman-natarajan/doctane.git
2 Virtual Env
python -m venv venv && venv\Scripts\activate
3 Install
pip install -r requirements.txt && pip install -e .
4 Run
python api/main.py
⚙️ Environment Variables
| Variable | Description | Default |
|---|---|---|
| BUILD_VERSION | Package version | 0.1.0a0 |
| CHECKPOINT_DIR | Model checkpoints | ./checkpoints |
| DATA_DIR | Training data | ./data |
| LOG_DIR | Training logs | ./logs |
💡 Infrastructure Required
Training requires GPU resources. Provide your own compute (local GPU, AWS, GCP, Azure). We provide the code and training scripts - you bring the hardware.
🏋️ Training Models
Text Detection
python train/text_detection/train_detection.py --config configs/detection.yaml --epochs 100
Text Recognition
python train/text_recognition/train_recognition.py --config configs/recognition.yaml --epochs 50
Distributed (DDP)
torchrun --nproc_per_node=4 train/text_detection/train_detection_ddp.py --config configs/detection.yaml