-
Thank you for your brilliant work.
1. According to Figure 1 in the paper, for Visual Feature Embedding of image regions, VL-BERT is using features of bounding box proposals. It seems you are concate…
-
Hi,
In `Pre-training VL-BERT` section, you've highlighed some tasks on which model was trained.
1. Pretraining on Conceptual Conceptions
2. Masked Language Modeling with Visual Clues
3. Mask…
-
Sample snippets to reproduce the inconsistency issue:
```
import random
import mxnet as mx
import numpy as np
import gluonnlp as nlp
import uuid
# mx.__version__ '1.5.0' (mxnet-cu100mkl)
…
-
hi all:
I use ubuntu 18.04 comolie source code failed!!
this is output message, please help me how to solve it ...
----
> ====== making target debian/stamp/conf/minimal_debian [new prereqs: ]==…
-
Thank the authors for providing us so cool matlab based deep learning toolbox. It is actually of great help to someone like me who is familiar with matlab.
I have a suggestion. Now the examples you p…
-
I want to build an encoder-decoder architecture with a 1x1xD intermediate representation. It doesn't seem to be possible to upsample this patch with the vl_nnconvt layer. Is this an implementation iss…
-
Hi all,
I understand that you can obtain the probabilites by replacing the 'softmax loss' by 'softmax' at the end on a sample by sample basis.
However, if i were to do the same on a pixel by pixel b…