Pinned issues
Issues
- 3
- 1
Can't download spider and model_weights
#61 opened by Fjakob - 0
How to get RA Tree node embeddings?
#60 opened by abs-xyz - 0
Issue in running Colab
#59 opened by abs-xyz - 0
- 0
Meaning of tensor beam_scores_el
#57 opened by ManasiPat - 3
How to get the confidence of a prediction?
#28 opened by entslscheia - 1
Problems using SmBop without values
#56 opened by CeadeS - 2
Executing exec.py
#55 opened by surajjkumar - 2
- 2
Question regarding final_beam_acc and BEM
#53 opened by awasthiabhijeet - 18
Is it possible to use the schema of our own dataset, generated by SQLite in json format, with SmBop code in google colab?
#20 opened by varunpandya2004 - 0
System requirements for faster training!
#52 opened by alan-ai-learner - 0
setting bug
#51 opened by hellosaferide - 20
Question about train/validation set.
#9 opened by PedroEstevesPT - 11
[Possible Bug?] Should is_level_order_list always have atleast one element as 1?
#49 opened by awasthiabhijeet - 7
Model Performance
#47 opened by alan-ai-learner - 3
- 4
- 3
Is SmBop can adapt the database functions and it not detecting the date columns in data base?
#45 opened by alan-ai-learner - 12
Do we have to create the schema manually for the custom database or is there any way to generate sqlite schema?
#39 opened by alan-ai-learner - 2
How do I make predictions on Custom Data
#29 opened by nikhilcss97 - 6
- 8
About multi GPUs for training
#14 opened by Young1993 - 8
Extract beam instead of best query
#10 opened by PedroEstevesPT - 1
How can i fine-tune model?
#38 opened by TemaDobryyR - 0
[possible bug?] is_level_order_list should always have atleast one element as 1?
#48 opened by awasthiabhijeet - 2
Resume training with the pretrained model
#22 opened by PedroEstevesPT - 1
Usage of vocab built during training
#46 opened by ali6947 - 1
Is it possible to use any other databases like MySQL, Postgresql, oracle etc
#42 opened by alan-ai-learner - 1
Type of enc object in 'forward' in smbop.py is a dict with the tensors. But the _read function yields TextField with strings for 'enc' in the returned Instance. Where does this change take place and how to change the tokeniser used here?
#36 opened by ali6947 - 1
In smbop.py, line 865 has the comment "TODO: change this!! this causes bugs!" Exactly what bug is this?
#41 opened by ali6947 - 1
What is the purpose of the 2 lists "RULES_novalues" and "RULES_values" in node_util.py? could you please elaborate on its format and what do the 2 terms in each inner list denote
#40 opened by ali6947 - 1
- 2
Running SmBoP in multi-threaded contexts
#34 opened by spectraldoy - 2
- 1
What are the uses of the function compute_beam_idx and compute_op_idx durin training ?
#33 opened by ali6947 - 5
why add “added_values”
#11 opened by Young1993 - 0
- 2
Hos is reranking applied in the code?
#27 opened by entslscheia - 1
EM evaluation failed
#25 opened by realningzheng - 6
CUDA out of memory. Tried to allocate 20.00 MiB (GPU 0; 2.00 GiB total capacity; 1.24 GiB already allocated; 4.50 MiB free; 1.24 GiB reserved in total by PyTorch)
#24 opened by anumi1999 - 3
Example of config.json for resume.py
#23 opened by Illumaria - 2
- 3
- 3
Resuming model training
#7 opened by PedroEstevesPT - 2
The problem of reproducibility.
#5 opened by huybery - 3
- 2
Is it possible to share the trained model?
#3 opened by shuqinlee