Mask TextSpotter v3 

Known as the strongest end-to-end Text recognition Model

Actual test , The detection effect is really extraordinary , Slightly worse in speed than ABCNet. Let's see the effect first

There are also some missed inspections . But the first picture , This is actually detected , It's still very powerful , Need to know ABCNet Yes, in the first picture , The test is really bad .

Speed , as follows ,

ABC：

mst:

The environment and script are as follows ： 

Python3 (Python3.7 is recommended)
PyTorch >= 1.4 (1.4 is recommended)
cocoapi
yacs
matplotlib
GCC >= 4.9 (This is very important!)
OpenCV
CUDA >= 9.0 (10.0.130 is recommended)


my env:
torch                  1.4.0
torchvision            0.5.0

py362
python                 3.6.2
cuda                   10.1

git clone https://github.com/NVIDIA/apex.git
cd apex
python setup.py install --cuda_ext --cpp_ext
#  Be careful ：apex Compile in torch==1.5.1 torchvision==0.6.1 Under the 

cd MaskTextSpotterV3
 # build
  python setup.py build develop


# demo :a single image inference by python tools/demo.py
eg:
# 1.single image:
python tools/demo.py --image_path ./demo_images/img_77.jpg --visu_path ./demo_images/img_77_res.jpg
# 2.image folder
eg:
python tools/demo.py --input ./demo_images/ --output ./out/demo_out

# test
python tools/test_net.py --config-file configs/mixtrain/seg_rec_poly_fuse_feature.yaml



# train

# 1.Trained with SynthText

python3 -m torch.distributed.launch --nproc_per_node=8 tools/train_net.py --config-file configs/pretrain/seg_rec_poly_fuse_feature.yaml

Training part , Not yet .