Manli Shu issues

Repositories
Issues
Comments

Results 2 issues of


                                            Manli Shu

the implementation of batch normalization in your model

Hi, I have a little question about the BatchNorm layer in the model. In ./colorization/models/colorization_train_val_v2.prototxt, I noticed that you are using `BatchNorm` layers without `Scale` layers following behind, so does...

A question regarding the implementation of spatial-aware attention in LayoutLMv2

Hello there, Thank you all for releasing the code of these impactful works. When using one of your implementations, I came across [this line](https://github.com/microsoft/unilm/blob/4301ebe1a832b7bcb33be0ab3a460306d467a912/layoutlmft/layoutlmft/models/layoutlmv2/modeling_layoutlmv2.py#L323), for which I'm not sure if...