I am trying to reproduce the training code without using FastAI.learner
I use pretrained best-train-abinet.pth released version with the corresponding config file. And it's my reproduce training code:
`
I used the MJ + ST data set, to test training with the above code, however, the evaluation results every 500 iterations on benchmark sets decreased relatively negatively. I don't know if my reimplementation have any thing wrong.
Now my issue is solved. I realized I accidentally set ignore_index for null_char in criterion, it causes the model to fail to converge for the stop of recognition string.
Hi @FangShancheng,
I am trying to reproduce the training code without using FastAI.learner I use pretrained best-train-abinet.pth released version with the corresponding config file. And it's my reproduce training code:
` criterion = MultiLosses(one_hot= True, device= device) .... images_source_tensor, labels_source = next(source_loader_iter) images_source = images_source_tensor.to(device)
` I used the MJ + ST data set, to test training with the above code, however, the evaluation results every 500 iterations on benchmark sets decreased relatively negatively. I don't know if my reimplementation have any thing wrong.
Thanks.