-
Hi there,
Thank you for this wonderful registry.
Recently I have been developing [MultiMolecule](multimolecule.danling.org).
[MultiMolecule](multimolecule.danling.org) is designed to be a …
-
I know BERT has achieved SOTA in many NLP tasks, such as SQuAD and SWAG.
But note that the data (both training and test) of SQuAD is from **Wikipedia**, and that of SWAG is from the **BookCorpus**, a…
-
The current augmentation is so strong that the model barely learns anything (high loss, accuracy increases like
-
Hello, I ran the code directly using the setting pretrain_vision_model.yaml, here are the results of the trained model:
Benchmark | Accuracy |
IC13 | 92.6 |
SVT | 87.2 |
IIIT | 88.1 |
IC15 | 78…
-
Hi, I read the code but i can hardly find the definitions of neural network modules (encoder and decoder in intention estimator) and the parameters. It seems that the neural network modules are not in…
-
I have some issues in loading the local model as follows. Since the MiDaS repository is also downloaded from the Internet. However, in this case, unsuccessful Internet access does not result in an err…
-
Hello,
First, thanks for all your work!
I do have one issue...
When using Swedish language I get error:
PHP Warning: mb_eregi_replace(): Pattern is not valid under UTF-8 encoding in /vendo…
-
Amazing work! When do you expect phase II to be published, please? :)
-
Dear authors,
Congratulations on your interesting work, cheers!
I wonder your work would further benefit the community by altering a bit to do SSL pre-training.
As the original Jagsaw Puzzle p…
-
@lukaszkaiser
This is to illustrate what I have discussed on gitter.
Working with WMT EN-FR, I have observed the following.
You can replicate the paper results with "transformer -base" with 4 GP…