roatienza / deep-text-recognition-benchmark

PyTorch code of my ICDAR 2021 paper Vision Transformer for Fast and Efficient Scene Text Recognition (ViTSTR)
Apache License 2.0
284 stars 57 forks source link

Did you compare the result of CTC loss and cross entropy loss ? #17

Open Jiakui opened 2 years ago

Jiakui commented 2 years ago

In the paper, you mentioned that, you can either use CTC loss or cross entropy loss, did you compare the performance of the two different function, which one is better?

Thanks!