CRAFT-Reimplementation icon indicating copy to clipboard operation
CRAFT-Reimplementation copied to clipboard

fine-tuning on a custom dataset with the official craft-pytorch weights

Open alikaz3mi opened this issue 4 years ago • 4 comments

Hello, is it possible to fine-tune your model on a custom dataset with Craft-PyTorch released weights too?

alikaz3mi avatar Aug 09 '21 04:08 alikaz3mi

Yes, I just made it using the IC15 traing code. I labeled my dataset the same format as IC15.

gl94 avatar Sep 03 '21 07:09 gl94

Hello, gl94. Can you explain how did you manage do to it and if it works well ?

tahakoudri avatar Apr 07 '22 08:04 tahakoudri

Hello, gl94. Can you explain how did you manage do to it and if it works well ?

It's kinda a little bit tricky, you need to use the old branch of this repo, and change some code in the trainic15data.py and maybe some function in the dataloader to get a better model. After all this been done you'll find that craft is really hard to train. I rather recommend you using dbnet in the PPocr. It's easy to train and performs very well.

gl94 avatar May 19 '22 12:05 gl94

@gl94 What is PPocr?

SkygirlLuna avatar Jan 18 '23 16:01 SkygirlLuna