Attention-OCR
Attention-OCR copied to clipboard
Hello, I found that the same pair of images twice predicted results may be different, the reason for this problem is what? What is the current accuracy of the method you are tuned to?
The problem is solved. The problem appears ”cnn_model = CNN(self.img_data, not self.forward_only) #(True))”. svt accuracy:from 67% to 75.6%
@You mean that change 'cnn_model = CNN(self.img_data, True) #(not self.forward_only))' to ”cnn_model = CNN(self.img_data, not self.forward_only) #(True))”?