Amit Agarwal

Thanks @laura-wang for the code . I wanted to request your help to understand the temporal statistics. The ```sts``` folder I can see the scripts for generating and calculating it....

@cuhk-hbsun sure !

@cuhk-hbsun created the PR #1134 . though its a very small change. I quickly ran the training for 2 epochs and it works as expected. Let me know if anything...

@cuhk-hbsun while going over the code I had another doubt in terms of understanding that I want to clarify https://github.com/open-mmlab/mmocr/blob/64fb6fffc06f168355c8e3d28f5b31f26536f485/mmocr/models/kie/heads/sdmgr_head.py#L113 1. As per my understanding the residue is kind of...

@cuhk-hbsun this might have been a missed notification, can you please check the last question and share your views on it ?

Can we include support for Transfer Learning for KIE ? Like we load the pretrained KIE model or different UNET & Bi-LSTM and train the GLCN or just linear layer...

@innerlee , there are actually two use cases, we can prioritize accordingly : 1. Fine Tune only the last linear layer with custom classes. This can be the last FC...

Another request would be to integrate the model graphs with TensorBoard Logging in the config so that it becomes more intuitive to understand the model architecture. Currently the TensorBoardHook only...

ohh that's great @gaotongxiao ! S should I create a ticket there or is it fine as @zhouzaida already has it in the plan ?

Hi @gaotongxiao , can we include this in the upcoming release : https://github.com/open-mmlab/mmocr/issues/248 It will usher more research in the Document AI domain if users can explore the framework in...