Open dagongji10 opened 4 years ago
@zhang0jhon Thanks for sharing a nice work! I plan to train my own datasets with AttentionOCR and when I modify
config.py
, I got some doubts:
restore_path
: how to use this para? Set it to /path/to/pretrained.ckpt? Need I changestarting_epoch
?steps_per_epoch
: I only have 2 GPUs, so setbatch_size=5
, and how to changesteps_per_epoch
? My datasets have 56030 samples, must I setsteps_per_epoch=56030/5
?warmup_steps
: how to use this para? Must it keep same withnum_epochs
?
your problem I don't know, but I want to know what is label tool of labeling you own datset. because I also want to train in my own dataset.
@zhang0jhon Thanks for sharing a nice work! I plan to train my own datasets with AttentionOCR and when I modify
config.py
, I got some doubts:restore_path
: how to use this para? Set it to /path/to/pretrained.ckpt? Need I changestarting_epoch
?steps_per_epoch
: I only have 2 GPUs, so setbatch_size=5
, and how to changesteps_per_epoch
? My datasets have 56030 samples, must I setsteps_per_epoch=56030/5
?warmup_steps
: how to use this para? Must it keep same withnum_epochs
?