ad1a15637a
Fix missing import
2019-03-01 16:09:58 -08:00
0866d8a4e8
Add more requirements
2019-03-01 16:08:58 -08:00
4bddbada45
Fix typo
2019-03-01 16:08:52 -08:00
ac3ac8c680
Add Stanford copyright to all files that we touched
2019-03-01 15:54:54 -08:00
8e2b519ac3
Add copyright notices to all files
...
Makes the license clear and explicit
2019-03-01 15:51:45 -08:00
99e39f9528
Move generic dataset outside of torchtext
...
There is no reason for it to live inside torchtext, and having it
outside will help with using torchtext as a library
2019-03-01 15:47:11 -08:00
afd39c8660
Add requirements.txt file
2019-03-01 15:43:02 -08:00
5447d0c37c
Add a "decanlp" script that calls out to the different subcommands
...
Usage:
- decanlp train ...
- decanlp predict ...
- decanlp convert-to-logical-forms ...
2019-03-01 15:43:02 -08:00
a5a203b099
Add setup.py
2019-03-01 15:43:02 -08:00
41b80bb4f4
Move all python files to a decanlp/ package
...
As per python conventions
2019-03-01 15:43:02 -08:00
a44bde6693
Don't import unused tensorflow
2019-03-01 15:22:02 -08:00
35fe30272b
satisfy travis
2019-03-01 15:08:31 -08:00
cf534b3523
Merge pull request #4 from Stanford-Mobisocial-IoT-Lab/wip/gcampax/cleanups
...
Cleanups, server support
2019-03-01 14:35:29 -08:00
c66dde4ca0
Make the server actually work
2019-03-01 12:33:18 -08:00
a0ff18f1fe
Remove too many redundant tensorboard scalars
...
Clutters the UI, wastes disk space and cycles
2019-03-01 12:33:18 -08:00
ca91b6e24f
Clean up some really ugly code in predict.py and server.py
2019-03-01 12:33:18 -08:00
61f93aca9b
train: compute the best validation metric during training, and use it for model selection
...
If a model is found to be better than the previous one, save it
as "best.pth"
Model selection should happen at training time rather than validation
time so we can safely discard checkpoints after training (because
they take too much space)
2019-03-01 12:33:18 -08:00
d4b35d7ae6
train: don't save per-worker checkpoints if we're not doing distributed training
...
Saves disk space
2019-03-01 10:51:12 -08:00
a36f2efb8c
Add a simple json-based RPC server to handle interactive predictions
2019-03-01 10:46:16 -08:00
9a9b77ec17
Almond: load data from the TSV files directly
...
Almond is not a translation task, it's a semantic parsing task.
And it has its own established on-disk file format, and we should
respect that, instead of messing with .tt files
2019-03-01 09:36:14 -08:00
73d94f187b
SummaryWriter: replace add_scalars with add_scalar
...
tensorboardX's add_scalars is bonkers, and will create a different
file for each tag, which makes the tensorboard completely unreadable
(See https://github.com/lanpa/tensorboardX/issues/366 )
Instead, use add_scalar(), which puts everything in the same file,
as tensorboard is designed to do.
2019-03-01 08:44:06 -08:00
ae4bbfea3a
arguments: remove bad ugly log dir messing
...
Stick with what the user says as the --save directory. If the user
needs, they can provide the timestamp on the command line.
2019-03-01 08:30:35 -08:00
7738b66e72
updates
2019-02-28 19:52:13 -08:00
d2656bb53a
update post_process_decoded_results.py
2019-02-27 12:01:42 -08:00
26f57a3059
don't shuffle dataset during prediction
2019-02-27 11:17:38 -08:00
eff58ba1eb
merge updates
2019-02-27 10:54:01 -08:00
2ef63c660e
export results to csv files
2019-02-27 10:52:38 -08:00
fede42e471
add cached option for predict
2019-02-20 11:22:32 -08:00
b8f4c1b0e5
fix max-margin loss implementation
2019-02-20 11:06:49 -08:00
f47da57330
fix bug for joining paths
2019-02-19 16:21:34 -08:00
ad5c9c6dc1
save cached files to an assigned path
...
useful when you don't have write permissions to dataset directory
2019-02-19 15:55:20 -08:00
f3545ad9d3
add max-margin loss
2019-02-19 13:48:52 -08:00
f2335e456b
Merge pull request #1 from Stanford-Mobisocial-IoT-Lab/wip/field
...
Remove hacks needed to use a different tokenizer for Almond
2019-01-24 10:44:33 -08:00
e4afb21928
minor fix
2019-01-23 19:13:26 -08:00
8c54dc1391
updates and fixes
2019-01-23 16:41:37 -08:00
fdfdd154c4
Remove hacks needed to use a different tokenizer for Almond
...
Almond data is always pretokenized (because we must preprocess
numbers/quoted strings/etc.).
Previously, we used a bad HACK of hardcoding almond in the generic
Field subclass. Now, we instead thread through the tokenizer/detokenizer
arguments from the right places.
In the future, we will probably want task classes, to clean up
the mess of hacks and hardcoded task-specific tweaks everywhere.
2019-01-23 10:48:49 -08:00
91ad08211f
Fix duplicate elmo option
2019-01-23 10:45:30 -08:00
9ec8d7cf2d
Merge remote-tracking branch 'upstream/master'
2019-01-23 10:44:20 -08:00
09bcae5dd5
Merge branch 'master' into mehrad/master
2019-01-23 10:34:17 -08:00
cd997f257f
prepend root before save
2019-01-10 21:24:43 +00:00
eed545bbf7
log_dir needs root prefix
2019-01-09 18:06:04 +00:00
81b7ea7e72
options for sgd
2019-01-09 01:13:46 +00:00
27bb192249
unique val tasks
2019-01-09 00:28:11 +00:00
287b911d9c
separate out root dir; add option for experiment name
2019-01-08 02:05:55 +00:00
873236860a
fix cuda error
2018-12-18 14:56:29 -08:00
b4bb1ad661
working version of differentiable BLEU loss
2018-12-17 16:43:06 -08:00
07dd886f9a
Update README.md
2018-12-12 12:31:44 -08:00
c096a1f5ba
bugs in overwrite; new best mqan model
2018-12-12 20:29:46 +00:00
1dc5f7d28e
moving schema raw files to s3; updated pretrained models
2018-12-10 21:52:34 +00:00
1bd922b5bc
back compat predict.py
2018-12-10 19:41:27 +00:00
Giovanni Campagna