bentrevett
fe430c603e
added explicit notes to copy embeddings using weight.data and not weight
2019-09-19 16:32:07 +01:00
bentrevett
ed9455e89a
non-deterministic error fixed in latest cudnn version
2019-09-19 16:16:22 +01:00
bentrevett
2753e93ca4
reran all notebooks with latest pytorch and torchtext to ensure still working
2019-09-16 11:32:18 +01:00
bentrevett
5b0af623a9
updated readme to note latest versions of pytorch and torchtext are being used
2019-09-16 11:31:54 +01:00
bentrevett
b1db529eee
removed unnecessary squeeze in rnn forward method
2019-07-10 13:10:30 +01:00
bentrevett
808aaafa6f
removed extra print statement added whilst debugging. changed default model back to 2d cnn
2019-04-22 14:27:48 +01:00
bentrevett
807ec2082a
fixed typos in max pool figure and size of tensors after convolutional filters ( #35 )
2019-04-22 13:26:13 +01:00
bentrevett
61093d819c
removed unnecessary torch.cuda.manual_seed from appendix c notebook
2019-04-16 10:10:59 +01:00
bentrevett
ed89d29f8d
added some reference links
2019-04-16 10:08:07 +01:00
bentrevett
a901a727e6
removed testing cell from notebook C, updated gitignore to ignore trained embeddings file
2019-04-16 09:57:20 +01:00
bentrevett
982083f52a
updated pytorch version
2019-04-16 09:37:43 +01:00
bentrevett
b337ea6976
updated readme to note bug in pytorch for tutorial 2
2019-04-10 15:35:24 +01:00
bentrevett
be122f3a6f
added model.eval() in predict sentiment functions ( #31 )
2019-04-10 10:27:20 +01:00
bentrevett
0e2e8f49ba
updated readme to link to appendix C
2019-04-02 13:39:51 +01:00
bentrevett
faaa6a1adc
added appendix c - handling embeddings
2019-04-02 13:36:14 +01:00
bentrevett
856d9e5598
updated appendix B - formatting and typos
2019-04-01 17:08:38 +01:00
bentrevett
669a9b8436
removed erroneous statement about the cnn model being the fastest model
2019-04-01 16:40:55 +01:00
bentrevett
36c8bf7cdc
updated readme for some more details on appendix b
2019-04-01 16:19:07 +01:00
bentrevett
9403847535
updated readme to mention the use of packed padded sequences in notebook 2
2019-04-01 16:18:02 +01:00
bentrevett
c429c70e73
changed some wording due to rerunning notebook 2 with packed padded sequences
2019-04-01 16:11:52 +01:00
bentrevett
c13c674a67
added packed padded sequences to notebook 2
2019-04-01 16:08:53 +01:00
bentrevett
63c08ef0bc
mentioned how notebook 2 will introduce packed padded sequences
2019-04-01 16:08:30 +01:00
bentrevett
525ae0b416
lots of formatting changes
2019-03-29 16:57:00 +00:00
bentrevett
eea44cb487
added missing unk init and fixed some formatting to notebook 4
2019-03-29 16:37:21 +00:00
bentrevett
b21f42f764
mention how using sort key is preferred over sort = False
2019-03-23 14:48:52 +00:00
bentrevett
59920c56cf
removed incorrect xavier init example from notebook 2
2019-03-23 14:45:52 +00:00
bentrevett
b9d46f0ce0
added need for sort/sort_key in iterators when using own dataset ( #27 )
2019-03-23 10:06:34 +00:00
bentrevett
bf8cc46e48
added parameter count and epoch timer functions to all notebooks. also added cnn1d imlementation to notebook 4
2019-03-21 22:48:21 +00:00
bentrevett
cd09d20b65
fixed out of glove vector initialization and missing generate bigrams functions in fasttext implementation
2019-03-21 17:22:25 +00:00
bentrevett
5e7c5a9fcf
added text to multi-class notebook
2019-03-10 17:30:07 +00:00
bentrevett
6e037d8386
fixed wording and updated assets for notebook 4
2019-03-10 16:28:21 +00:00
bentrevett
ce7ce974c0
updated readme to mention multiclass notebook
2019-03-10 15:46:11 +00:00
bentrevett
977613215e
updated assets and wording for notebook 3
2019-03-10 15:45:40 +00:00
bentrevett
14edc64ff8
fixed wording on notebook 2
2019-03-10 15:37:09 +00:00
bentrevett
25efef84d4
changed imgur urls to own assets
2019-03-10 14:45:44 +00:00
bentrevett
0327a54c63
fixed some wording
2019-03-10 14:16:18 +00:00
bentrevett
61ee0e66a5
Merge branch 'master' of https://github.com/bentrevett/pytorch-sentiment-analysis
2019-01-25 14:00:11 +00:00
bentrevett
8220b98d2a
added rough draft of multi-class notebook
2019-01-25 13:56:46 +00:00
Ben Trevett
7afa650a34
Merge pull request #13 from zdepablo/master
...
Removed an incomplete phrase (#1 )
2018-12-10 23:19:02 +00:00
César de Pablo
5571f93cb8
Remove an incomplete phrase ( #1 )
2018-12-08 22:16:55 +01:00
bentrevett
7dd3c19876
fixed typo
2018-11-22 21:15:45 +00:00
bentrevett
ecbfa2e469
Appendix A typos
...
- forgot to change train, valid and test to train_data, valid_data and test_data
2018-10-17 18:02:22 +01:00
bentrevett
61bf7da1d0
Update for TorchText 0.3
...
- reworded a lot of the explanations
- fixed a lot of typos
- updated some images and moved new ones to assets folder
- fixed deterministic evaluation with `torch.backends.cudnn.deterministic = True`
- tensor_type in Fields becomes dtype
- changed train, valid, test TorchText dataset objects to be named train_data, valid_data and test_data
- TorchText iterators now have `repeat = False` by default, so removed
- TorchText iterators now take a `torch.device` instead of an int representing the GPU number (and -1 for CPU)
- `F.sigmoid` is now `torch.sigmoid`
- padding sentences in the CNN model is now fixed (before spaCy would tokenize the <pad> token into three separate tokens)
2018-10-17 17:54:31 +01:00
bentrevett
710ead1daa
typo in readme
2018-07-19 19:19:49 +01:00
bentrevett
9f71d9d5e8
fixed typo in CNN model (thanks Remy) and changed size of tensor comments to use n_filters instead of n_channels, reflecting the actual variable names used
2018-07-19 17:23:16 +01:00
bentrevett
6c7141e5db
updated readme to detail the 3rd and 4th tutorials
2018-07-05 17:22:09 +01:00
bentrevett
af61b05728
updated readme to add link to tutorial 4
2018-07-05 17:17:56 +01:00
bentrevett
8fc3a75721
typo in conv tutorial about calculating output size of conv layers
2018-07-05 17:16:10 +01:00
bentrevett
f34d972d74
added conv tutorial
2018-07-05 17:12:00 +01:00
bentrevett
01c6f59c69
fixed train/valid splits not being deterministic
2018-07-05 12:47:04 +01:00
