Open HSILA opened 3 years ago
I tried training from scratch without fine-tuning (same characters). Again when I try to infer with demo.py
, it just produces numerical predictions, while my character list contains letters too.
Is it a bug or am I doing something wrong?
Hi First I fine-tuned the None-VGG-BiLSTM-CTC on pre-trained weights with these characters:
+-/0123456789ABCDEFGHJKLMNPQRSTUVWYZ
I have a test set (besides eval) and I want to test the model's performance. When I use
demo.py
for inference and hard-code the above characters intodemo.py
and run:The log is saved on
log_demo_result.txt
. There's an odd observation:I fine-tuned on uppercase characters and changed
--character
in bothdemo.py
andtrain.py
but most of the predicted labels contain lowercase characters. Can anybody explain why?