Hello there! Great work. I'd like to ask how to train the alig

<a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/us

Predict More Characters about matrn HOT 4 CLOSED

Mountchicken commented on August 19, 2024

Predict More Characters

from matrn.

Comments (4)

yiren556 commented on August 19, 2024

How many epochs can you train? After I modify the epoch, it always ends after epoch9

from matrn.

Mountchicken commented on August 19, 2024

@yiren556
I didn't modify any hyperparameters and the training ended at the 9th epoch.

from matrn.

yiren556 commented on August 19, 2024

This is the result of my debugging, I don't understand why it stops

from matrn.

byeonghu-na commented on August 19, 2024

Hi, sorry for late reply and thank you for your interest.

I think you may change charset_path in template.yaml from 'data/charset_62.text' to your own charset, and case_sensitive to True.

As you know, pre-trained language and vision models are trained on 36 characters. Therefore, you need to train these pre-trained models on 90 characters, or you may load these pre-trained models without the final classification layer, which is related to the size of character set.

I think this link is useful to ignore size mismatch problem. (Lightning-AI/pytorch-lightning#4690 (comment))
Apply this methods to loading pre-trained model, which are in below:

MATRN/modules/model.py

Lines 17 to 19 in 57b6b8e

    
           def load(self, source, device=None, strict=True): 
        
               state = torch.load(source, map_location=device) 
        
               self.load_state_dict(state['model'], strict=strict)