Jianquan Ye

> @JiaquanYe do you modify code in mmdetection-2.11.0 . Which code you modify .I use mmocr-0.4 so it must mmdet-2.18.1 Yes, I have modify the mmocr and mmdetection source code....

> Thanks for your great work! > > How about the inference speed ? I use a GTX-1080 and it cost a few seconds(almost 10s) per image. So I want...

> > In the competition, we used our own internal tool (FastOCR) to implement our algorithm. In the mmocr framework, we did not implement it. If you fully understand the...

> I implement Decoder part of MASTER-pytorch in FasterTransformer, compare to origin pytorch it's **much faster**. [Example code](https://github.com/Sanster/FasterTransformer/tree/v4.0-master-example/sample/pytorch/master_example)。It should be easy to add to TableMASTER with the minor changes It's...

Maybe you can try to use the docker environment by 'docker pull jiaquanye/tablemaster_mmocr:v1' The predict box location is abnormal. Maybe you can check your visualization code.

You can save html result like [this](https://github.com/JiaquanYe/TableMASTER-mmocr/blob/689f49cd4f632272244e758551d5e3c92211b7c2/table_recognition/demo/demo.py#L78-L84)

Hi, all the .sh file have been moved to './table_recognition/expr' folder.

> @delveintodetail Can you please add specific details on the `cfg` in the `table_inference.py`? > I find it difficult to identify where to use the pretrained `pth` file. Something like...

> @JiaquanYe > > Where can I find the config file for the checkpoint available in google drive? > > Is it this one? `TableMASTER-mmocr/configs/textrecog/master/table_master_lmdb_ResnetExtract_Ranger_0930.py`? I train this model with...

> Thanks your work! > > Firstly, I run the `data_preprocess.py` to get valid train data, and get the same directory structure, like this: > > ``` > mmocr_pubtabnet_recognition_0726 >...