search

cs-chan / Total-Text-Dataset

Total Text Dataset. It consists of 1555 images with more than 3 different text orientations: Horizontal, Multi-Oriented, and Curved, one of a kind.
BSD 3-Clause "New" or "Revised" License
747 stars 140 forks source link

Don't know how to evaluate by Python #6

Closed xieenze closed 6 years ago

xieenze commented 6 years ago

I see there is an example floder in Evaluation_Protocol, but in Python_scripts, I don't know where you read them. Can you give us some simple examples about how to evaluate by Python?
Thank you very much.

ckchng commented 6 years ago

The first three lines of the python script is for you to set the necessary directories.

As I've listed in the comment: 'input_dir' is where you keep your detection text files. 'gt_dir' is where you keep the ground-truths (provided by us). 'fid_path' can be any place you want it to be. It contains per image result.

Your detection file should have the name of 'img(id).txt'. For instance, img1.txt. The output should be stored in the form of 'y0,x0,y1,x1, .... yn,xn'

Let me know if this is clear enough for you.

xieenze commented 6 years ago

Thanks, now I know it.