Features Pipeline Models Get Started Profile GitHub Docs

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

VariableDescriptionDefault
BUILD_VERSIONPackage version0.1.0a0
CHECKPOINT_DIRModel checkpoints./checkpoints
DATA_DIRTraining data./data
LOG_DIRTraining 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