• Hardware (L4)
• Network Type (ocrnet)
• Training spec file :
I wonder why my model does not train well on long sentences even though I have set in the config max_label_length: 200 (number of characters in my longest label). This is my log training:
Could you set a larger input_width and retry?
There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.
