Skip to content

resolved 0 dimension error in repackage hidden #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ghost wants to merge 3 commits into
base: master
Choose a base branch
from
Open

resolved 0 dimension error in repackage hidden #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
98913c4
Update README.md
ashray17aman Jun 25, 2019
c52bbed
Update README.md
ashray17aman Jun 25, 2019
9c44e01
Update ptb-lm.py
ashray17aman Jun 25, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,4 +21,4 @@ On GTX 1080 I am getting around 7,400 wps.

## Requirements
* Python 3 (I used Anaconda distribution)
* PyTorch (I used 0.1.12)
* PyTorch (I used 0.1.12)
19 changes: 15 additions & 4 deletions ptb-lm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,9 +7,10 @@
from lm import repackage_hidden, LM_LSTM
import reader
import numpy as np
import copy

parser = argparse.ArgumentParser(description='Simplest LSTM-based language model in PyTorch')
parser.add_argument('--data', type=str, default='data',
parser.add_argument('--data', type=str, default='data/penn-treebank/',
help='location of the data corpus')
parser.add_argument('--hidden_size', type=int, default=1500,
help='size of word embeddings')
Expand Down Expand Up @@ -39,18 +40,28 @@ def run_epoch(model, data, is_train=False, lr=1.0):
epoch_size = ((len(data) // model.batch_size) - 1) // model.num_steps
start_time = time.time()
hidden = model.init_hidden()
savehidden = copy.deepcopy(hidden)
costs = 0.0
iters = 0
for step, (x, y) in enumerate(reader.ptb_iterator(data, model.batch_size, model.num_steps)):
#print(x,y)

inputs = Variable(torch.from_numpy(x.astype(np.int64)).transpose(0, 1).contiguous()).cuda()
model.zero_grad()
hidden = repackage_hidden(hidden)
#print(hidden)
#print(x,' x ', y, ' print x and y')
'''
hidden = repackage_hidden(hidden)
modified - ashray17aman
'''
hidden = copy.deepcopy(savehidden)
outputs, hidden = model(inputs, hidden)
targets = Variable(torch.from_numpy(y.astype(np.int64)).transpose(0, 1).contiguous()).cuda()
tt = torch.squeeze(targets.view(-1, model.batch_size * model.num_steps))

loss = criterion(outputs.view(-1, model.vocab_size), tt)
costs += loss.data[0] * model.num_steps
#print(loss)
costs += torch.Tensor.item(loss.data) * model.num_steps
iters += model.num_steps

if is_train:
Expand Down Expand Up @@ -90,4 +101,4 @@ def run_epoch(model, data, is_train=False, lr=1.0):
print('Test Perplexity: {:8.2f}'.format(run_epoch(model, test_data)))
with open(args.save, 'wb') as f:
torch.save(model, f)
print("########## Done! ##########################")
print("########## Done! ##########################")