Make awesome things that matter.

• Modify some configuration in config.yaml

make train

make test-all

• For evaluation metric, please refer to MegReader repository

# iou-based Pascal
make ioueval

# overlap-based DetEval
make deteval

Heatmap	Polygon	Rotated rectangle

Image origin	Text-line detected

• Recognition model was trained on MJSynth and SynthText dataset

# for TotalText dataset
make deteval

• Support datasets
  • TotalText
  • ICDAR2015
  • SCUT-CTW1500
  • MSRA-TD500
  • COCO-Text
  • Synthtext
  • ArT2019 (included Total-Text, SCUT-CTW1500 and Baidu Curved Scene Text dataset)
• Pytorch-lightning
• Model serving with Torchserve
• Metric callback (P/R/F1)
• IoU-based metric (P/R/F1 - Pascal)
• Overlap-based metric (P/R/F1 - DetEval)
• Model quantization
• Model pruning
• Docker / docker-compose
• ONNX, TensorRT
• Text recognition model

I got a lot of code from DBNet.pytorch, thanks to @WenmuZhou

• Real-time Scene Text Detection with Differentiable Binarization
• Evaluation metrics
• DBNet.pytorch
• DBNet.keras
• Real-time-Text-Detection
• PSENet.pytorch
• deep-text-recognition-benchmark
• volksdep
• TedEval
• torch2trt