Introduction

This is a PyTorch implementation of FOTS.

• [x] ICDAR Dataset
• [x] SynthText 800K Dataset
• [x] detection branch
• [x] recognition branch
• [x] eval
• [x] multi-gpu training
• [x] reasonable project structure
• [x] wandb
• [x] pytorch_lightning
• [x] eval with different scales
• [ ] OHEM

Instruction

Requirements

conda create --name fots --file spec-file.txt
conda activate fots
pip install -r reqs.txt

cd FOTS/rroi_align
python build.py develop

Training

# quite easy, for single gpu training set gpus to [0]. 0 is the id of your gpu.
python train.py -c pretrain.json
python train.py -c finetune.json

Evaluation

python eval.py 
-c finetune.json
-m 
-i 
--detection    
-o ./results
--cuda
--size "1280 720"
--bs 2
--gpu 1

with --detection flag to evaluate detection only or without flag to evaluate e2e

Benchmarking and Models

Belows are E2E Generic benchmarking results on the ICDAR2015. I pretrained on Synthtext (7 epochs). Pretrained model (code: 68ta). Finetuned (5000 epochs) model (code: s38c).

Samples

Acknowledgement

• https://github.com/SakuraRiven/EAST (Some codes are copied from here.)
• https://github.com/chenjun2hao/FOTS.pytorch.git (ROIRotate)