is the checkpoint right?
learn01one opened this issue · comments
hi,i met a problem when ran the demo:
size mismatch for rec_head.decoder.tgt_embedding.weight: copying a param with shape torch.Size([91, 256]) from checkpoint, the shape in current model is torch.Size([72, 256]).
any detaills i don't get?thanks
Which script specifically did you run?
Which script specifically did you run?
hi,the script:
./Experiment/Experiment2/Exper_2_STN_real_15_test.sh
the pretrained_model is :Real_15.pth.tar
Just try to uncomment line 33-34:
It may be that the model is the one we used in IC19 competition, which contains some rare characters.
Hi @learn01one
Did it help solve the problem?
Hi @learn01one
Did it help solve the problem?
maybe,i met other problem:
RuntimeError: Error(s) in loading state_dict for ModelBuilder
Can you provide some more details?