Jisu Hwang
Jisu Hwang
@peteanderson80 Hi, Thank you for sharing nice work. Is there any plan about object segmentation? I really want to do object detection with your simulator.
Hi, @gaotongxiao @YanShuang17 I'm confused that your issue. I'm not sure, but It looks like right that you coded before. Here's the[Clova's SATRN(origin repo)](https://github.com/clovaai/SATRN/blob/d4c257b2732137858827041f81761962a27f5228/src/networks/SATRN.py#L230), I think it looks same with...
Now, I understand In your [repo ](https://github.com/open-mmlab/mmocr/blob/c6c4acd39b1c56fec1b87530b2d241fe8af4ceed/mmocr/models/textrecog/layers/satrn_layers.py#L163), it looks like you already summed the input tensor and positional tensor, right? If this right, then the code should be changed as...
is this still not fixed? I got same error.
Hi, @guoxiaolu Did you fix the problem?
@NielsRogge I think it still have a problem that the processor output's size don't match each others. Also, the encoded_inputs still doesn't have the token_type_ids key. if it is fixed,...
@jyotiyadav94 @aditya11ad Did you get solution? I saw the colab(from @avinashok), but i can't find the way to extract Key-Value pairs.
@jyotiyadav94 Thank you for sharing idea. Is this library also available in another OCR?(Not tesseract OCR, I got seperated OCR results)
@jyotiyadav94 Sure, the contact mail is at the top of my profile readme. Thank you :)
@nurielw05 I saw really late. jyoti shared [this link](https://github.com/Vishnunkumar/doc_transformers/blob/main/doc_transformers/form_parser.py) which is related with above post.