Tweak conv-rnn model #75
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Member
daemon
commented
Oct 29, 2017
daemon
commented
- Fix misplaced zero_grad()
- Tweak model hyperparams and optimization algorithm
- Fix misplaced zero_grad() - Tweak model hyperparams and optimization algorithm
tuzhucheng
reviewed
Oct 29, 2017
conv_rnn/test.py
Outdated
| @@ -17,19 +18,19 @@ def main(): | |||
| parser.add_argument("--gpu_number", default=0, type=int) | |||
| args = parser.parse_args() | |||
|
|
|||
| model.set_seed(5, no_cuda=args.no_cuda) | |||
| data_loader = data.SSTDataLoader(args.data_dir) | |||
| model.set_seed(3, no_cuda=args.no_cuda) | |||
There was a problem hiding this comment.
Actually the seed is useless in test.py, I'll remove it later.
| @@ -34,8 +34,6 @@ def __init__(self, word_model, **config): | |||
| else: | |||
| raise ValueError("RNN type must be one of LSTM or GRU") | |||
| self.conv = nn.Conv2d(1, n_fmaps, (1, self.hidden_size * 2)) | |||
| if dropout: | |||
There was a problem hiding this comment.
does this hurt performance? if we are removing it why are we adding --dropout_prob to train.py?
There was a problem hiding this comment.
Paper says no dropout for SST1/2.
tuzhucheng
approved these changes
Oct 29, 2017
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.