zhengshangdong

@Fighting-JJ Hi,bro.I trained on dataset synth90k too.But the loss is always 12.Even I divide the trainsets into 7,000,000 or 800,000 or 5000 pictures,the loss was not change.And the accuray is...

@munziliashali Hi,if you use batchNormalization=True,the pretrained model can not load straightly,how you solve this new problem.....Only one way I can come out——rebuild the network and get the convs(weights bias) from...

sorry,sir.It's my fault.I get the false labels....I thought the dataset——Synth90k is all number picture,so I wrote ： index = imagePath.find('.jpg') label = imagePath[index:index-4].It should be: imagePath.split('_')[-2].Thank you for your time....