efficientdensenet_crnn
efficientdensenet_crnn copied to clipboard
memory efficient densenet+lstm+ctc实现中文识别
Bumps [numpy](https://github.com/numpy/numpy) from 1.14.2 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...
Bumps [eventlet](https://github.com/eventlet/eventlet) from 0.20.1 to 0.31.0. Changelog Sourced from eventlet's changelog. 0.31.0 IMPORTANT: websocket: Limit maximum uncompressed frame length to 8MiB https://github.com/eventlet/eventlet/security/advisories/GHSA-9p9m-jm8w-94p2 0.30.3 wsgi: websocket ALREADY_HANDLED flag on corolocal green.ssl:...
''' RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument #2 'source' ''' Got this error on line 407 of `efficientdensenet_crnn/train/pytorch-train/models/efficient_densecrnn.py`, can you please help ?
> ''' > RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument #2 'source' > ''' > > Got this error on line 407 of `efficientdensenet_crnn/train/pytorch-train/models/efficient_densecrnn.py`, can...
请问densenet是如何与LSTM连接的?之间需要做哪些操作?是像CTPN中那样连接的吗
训练集问题
大佬能分享下,训练集的连接吗?谢谢
关于性能
你好,请问densenet有跟直接使用原作者的类vgg做比较吗,效果上会不会更好一点,有没有资料可以参考下?
可以直接训练吗
请问这个项目可以直接训练吗,训练效果怎么样。