re-continue train from the latest npz model file

Bartzi / see

Code for the AAAI 2018 publication "SEE: Towards Semi-Supervised End-to-End Scene Text Recognition"

GNU General Public License v3.0

574 stars 147 forks source link

re-continue train from the latest npz model file #43

Closed rezha130 closed 6 years ago

rezha130 commented 6 years ago

Hi @Bartzi

How to re-continue my trained epoch by using the latest npz model file?

This is the first command that i used on pervious train:

python train_text_recognition.py traindata/curriculum.json log \
--blank-label 0 \
--batch-size 16 \
--is-trainer-snapshot \
--use-dropout \
--char-map traindata/ctc_char_map.json \
--gpu 0 \
--snapshot-interval 1000 \
--dropout-ratio 0.2

Please help

rezha130 commented 6 years ago

ok, i got it using --resume