Skip to content

This is the github repository for converting craft pretrained model to tflite version

License

Notifications You must be signed in to change notification settings

tulasiram58827/craft_tflite

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

48 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CRAFT: Character-Region Awareness For Text detection

This is the github repository for converting craft pretrained model to tflite version and to provide an inference code using the tflite model.

The CRAFT model is proposed in this paper.

About CRAFT

The CRAFT model is a text detector that effectively detect text area by exploring each character region and affinity between characters. The bounding box of texts are obtained by simply finding minimum bounding rectangles on binary map after thresholding character region and affinity scores.

About the files

├── scripts
    ├── pytorch_to_onnx.py      --> Converts pretrained pytorch model to onnx.
    ├── onnx_to_tflite.py       --> Converts Onnx to TFLITE
    ├── tflite_inference.py     --> Inference with converted tflite model.
    ├── craft_inference.py      --> Inference with Pytorch Pretrained model.
 
 Corresponding `ipynb` files are provided in `colabs` folder.

├── models
   ├──  craft_mlt_25k.pth       --> Model trained on SynthText, IC13, IC17
   ├──  craft.tflite            --> TFLite Model (Dynamic Quantization)
   ├──  craft_float16.tflite    --> TFLite Model(Float16 Quantization)

Pretrained model can be downloaded from here

Results

PYTORCH MODEL OUTPUT
TFLITE MODEL OUTPUT (DYNAMIC QUANTIZATION)
TFLITE MODEL OUTPUT(FLOAT 16 QUANTIZATION)
TFLITE MODEL OUTPUT(INTEGER QUANTIZATION)

TFLITE PROFILER BENCHMARKS

DYNAMIC QUANTIZED TFLITE MODEL

References

Some portions of the code are taken from this repo

Citation

@inproceedings{baek2019character,
  title={Character Region Awareness for Text Detection},
  author={Baek, Youngmin and Lee, Bado and Han, Dongyoon and Yun, Sangdoo and Lee, Hwalsuk},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={9365--9374},
  year={2019}
}

If you found this project helpful or you learned something consider starring the repo.

About

This is the github repository for converting craft pretrained model to tflite version

Resources

License

Stars

Watchers

Forks

Packages

No packages published