We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
您好,我在用自己图片训练时,loss到0.01以下后,测试训练集内的数据,发现输出的文字有乱序现象。 训练图片是32*280,每张图至多10个字符。字符集大概400,包括汉字、标点、数字等。 乱序很多是三个字的: 123 会变成 132, 但也有12345变成51234的。 不知道是原因,请不吝赐教!
The text was updated successfully, but these errors were encountered:
乱序是有可能的,如果有多行文字一定会乱掉,图片以每32个像素从左向右扫描,如果同时扫描到两个新字符,那么他们的顺序是不能保证的
Sorry, something went wrong.
现在是32280的图像,只有一行文字,应该不会同时扫描到两个字符。我在DataLoader里把输入改成32256,测试结果还是有乱序。请问可以怎么解决? 另外,这个无法识别重复字符的问题,能解决吗?如果不能解决,那很多场合都没法用。
No branches or pull requests
您好,我在用自己图片训练时,loss到0.01以下后,测试训练集内的数据,发现输出的文字有乱序现象。
训练图片是32*280,每张图至多10个字符。字符集大概400,包括汉字、标点、数字等。
乱序很多是三个字的: 123 会变成 132, 但也有12345变成51234的。
不知道是原因,请不吝赐教!
The text was updated successfully, but these errors were encountered: