i have followed and did all the instructions exactly the same as custom_model.md
I always have problems:
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(RuntimeError: Error(s) in loading state_dict for Model:size mismatch for Prediction.weight: copying a param with shape torch.Size([97, 256]) from checkpoint, the shape in current model is torch.Size([99, 256]).size mismatch for Prediction.bias: copying a param with shape torch.Size([97]) from checkpoint, the shape in current model is torch.Size([99]).
What should I do? @rkcosmos
here my reader param:
easyocr.Reader(lang_list=["en"],gpu=False,model_storage_directory=EASYOCR_PATH+"model/",download_enabled=False,user_network_directory=EASYOCR_PATH+"user_network/",recog_network='custom_example')
Hi,
i have followed and did all the instructions exactly the same as custom_model.md
I always have problems:
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for Model:
size mismatch for Prediction.weight: copying a param with shape torch.Size([97, 256]) from checkpoint, the shape in current model is torch.Size([99, 256]).
size mismatch for Prediction.bias: copying a param with shape torch.Size([97]) from checkpoint, the shape in current model is torch.Size([99]).
What should I do? @rkcosmos
here my reader param:
easyocr.Reader(
lang_list=["en"],
gpu=False,
model_storage_directory=EASYOCR_PATH+"model/",
download_enabled=False,
user_network_directory=EASYOCR_PATH+"user_network/",
recog_network='custom_example'
)