tapas
tapas copied to clipboard
google-research
End-to-end neural table-text understanding models.
Hi -- I am trying to fine-tune the wikisql base model to accurately make predictions for tables that have up to 150 rows and have noticed that the prediction accuracy...
Hi, Are the numeric column ranks created based on the original table, or after `drop_rows_to_fit`? The reason I'm asking this is because in the Transformers library, some people are complaining...
Hello, I am trying to finetune the tapas_wtq_wikisql_sqa_masklm_medium_reset. Just to see, if it works in general, I wanted to finetune it on the same data it's already trained on, WTQ....
It seems that the `prev_checkpoint` is not be updated even if `checkpoint` is updated, which makes a checkpoint will be tested more than once some times.
Hello Team, Thanks for open sourcing this work! While I was running the notebooks shared along with the models, I noticed that the prediction time takes almost a minute to...
I want to use this model on my website, using JS, should I use tensorflow.js to write the predicting program from scratch or is there any other more suitable way?
Hi, I'm currently testing my implementation of `TapasTokenizer` (in the Transformers library, each model has a corresponding tokenizer that can be used to prepare data for the model). When testing...
Hi team, I have added a check so creating an empty dev file can be skipped in colab and this will reduce infer time as well. Thanks.
Hello, as a summer project (and to learn a lot about both Tensorflow and PyTorch), I am working on incorporating a PyTorch implementation of the TAPAS algorithm into the [Transformers...
I created a docker image to run TAPAS and wrote down instructions about how to use it at the README.md file.
Metadata
Owner
Metadata
End-to-end neural table-text understanding models.