how to feed the labels/annotation of the images during training?

sirius-ai / LPRNet_Pytorch

Pytorch Implementation For LPRNet, A High Performance And Lightweight License Plate Recognition Framework.

Apache License 2.0

908 stars 227 forks source link

how to feed the labels/annotation of the images during training? #53

Open tsan1 opened 3 years ago

tsan1 commented 3 years ago

Hi,

How do I feed the annotation text file during training? There is no argument to feed annotation file

mj-haghighi commented 3 years ago

Hi, I think your label should be your image name, just like samples in data/test directory. Label of the image is obtained by parsing the image name in __getitem__() function in LPRDataLoader You should also set your character set in load_data.py.