delveintodetail

Results 2 issues of delveintodetail

@delveintodetail Is there wrong in the predict.py file? _Originally posted by @li10141110 in https://github.com/fengxinjie/Transformer-OCR/issues/4#issuecomment-607083558_ for epoch in range(10000): model.train() run_epoch(train_dataloader, model, SimpleLossCompute(model.generator, criterion, model_opt)) model.eval() test_loss = run_epoch(val_dataloader, model, SimpleLossCompute(model.generator,...

SVTP has 645 images, if you carefully read each one, you will find there are around 20 images humans cannot recognize. How can this algorithm get 98.6%?? When seeing such...