Kaushal Kumar Prajapati

Same as multiclass classification with few modifications. 1. n_classes = 2, in last layer , self.out = nn.Linear(self.bert.config.hidden_size, n_classes), actually this will be automatically handled by the code for mutlicalss...

please attach the encode_plus function too

@ehildebrandtrojo can you please paste the table image without detection.

thanks @jpWang , Just a confusion though, the paper says  ``` In order to maintain the ability of LiLT to cooperate with different off-the-shelf text models in finetuning as...

Understood the concept Sir, but in code LiLT is adding **tmp_layout_attention_scores** to **attention_scores** ``` attention_scores = tmp_attention_scores + tmp_layout_attention_scores ``` does this not mean -- `tmp_layout_attention_scores` (layout attention) has influence...

I am sorry but I feel too dumb now :), unable to get the picture So when you say 1. The text flow needs to influence the layout flow in...

```layout_attention_scores = tmp_layout_attention_scores + tmp_attention_scores.detach()``` means 2) layout does not influence text in back-propagation; but we are detaching only `tmp_attention_scores` (text part) from back-propagation right, how does it stops tmp_layout_attention_scores...

did I ask something very dumb? @jpWang can you please point out the mistake or a resource that would help me understand

Very great post, nicely detailed and paced. Awesome job