Giter Site home page Giter Site logo

Comments (10)

JingyeChen avatar JingyeChen commented on July 24, 2024

YOUR_MODEL 是预训练模型的绝对路径

from fudanocr.

zhuxyme avatar zhuxyme commented on July 24, 2024

谢谢大佬!
我用你给出的模型进行测试,easy,medium,hard在CRNN下的识别率分别为0.5738,0.4564,0.347,和你论文中的有些不同。psnr和ssim也比你论文中的低一些。
Uploading 屏幕截图 2021-09-09 111219.jpg…

from fudanocr.

JingyeChen avatar JingyeChen commented on July 24, 2024

详见 issue #11 ,你可以看一下依赖库的版本是否正确,另外你可以看一下readme里上传的log文件

from fudanocr.

zhuxyme avatar zhuxyme commented on July 24, 2024

谢谢。
请问可以将ASTER和MORAN方式进行recognize的代码和模型也提供一下吗,我们准备引用你们的文章

from fudanocr.

JingyeChen avatar JingyeChen commented on July 24, 2024

感谢引用我们的工作
ASTER与MORAN的模型文件与代码在以下链接可以找到
https://github.com/ayumiymk/aster.pytorch
https://github.com/Canjie-Luo/MORAN_v2
我们是写脚本测试的,即训练完TBSRN后将生成的图片打包成lmdb,再送到这两个识别模型测试识别结果

from fudanocr.

Lz-2019317 avatar Lz-2019317 commented on July 24, 2024

感谢引用我们的工作
ASTER与MORAN的模型文件与代码在以下链接可以找到
https://github.com/ayumiymk/aster.pytorch
https://github.com/Canjie-Luo/MORAN_v2
我们是写脚本测试的,即训练完TBSRN后将生成的图片打包成lmdb,再送到这两个识别模型测试识别结果

那怎么输出生成的图片

from fudanocr.

JingyeChen avatar JingyeChen commented on July 24, 2024

super_resolution.py的第268行代码

images_lr = images_lr.to(self.device)
images_hr = images_hr.to(self.device)
sr_beigin = time.time()
images_sr = model(images_lr)
你需要可视化的话,把images_sr先转成PIL格式,再使用save函数保存到相应路径即可

最近事情比较多,没来得及更新,你可以先尝试一下 :D

from fudanocr.

zhuxyme avatar zhuxyme commented on July 24, 2024

感谢引用我们的工作
ASTER与MORAN的模型文件与代码在以下链接可以找到
https://github.com/ayumiymk/aster.pytorch
https://github.com/Canjie-Luo/MORAN_v2
我们是写脚本测试的,即训练完TBSRN后将生成的图片打包成lmdb,再送到这两个识别模型测试识别结果

那怎么输出生成的图片

请问可以提供测试图片对应的label吗。我自己将生成的图片转换成了mdb,但是没有对应的标签

from fudanocr.

JingyeChen avatar JingyeChen commented on July 24, 2024

您指的是TextZoom的测试图片嘛
TextZoom测试部分的lmdb数据集已经包含图片的label的

from fudanocr.

kanika02 avatar kanika02 commented on July 24, 2024

感谢引用我们的工作
ASTER与MORAN的模型文件与代码在以下链接可以找到
https://github.com/ayumiymk/aster.pytorch
https://github.com/Canjie-Luo/MORAN_v2
我们是写脚本测试的,即训练完TBSRN后将生成的图片打包成lmdb,再送到这两个识别模型测试识别结果

那怎么输出生成的图片

嘿,你得到输出图像了吗?请帮助我使用该代码生成输出图像。

from fudanocr.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.