Support for pytorch 1.0 scheduled?

[shirishr]

I am on pytorch 1.0 and no cuda.
When I run

python main.py --epochs 750 --data data/wikitext-2 --save WT2.pt --dropouth 0.2 --seed 1882

with --cuda set to action='store_true', default=False

I get an error:

RuntimeError: t() expects a 2D tensor, but self is 1D

Full trace as under:

Loading cached dataset...
Applying weight drop of 0.5 to weight_hh_l0
Applying weight drop of 0.5 to weight_hh_l0
Applying weight drop of 0.5 to weight_hh_l0
[WeightDrop(
(module): LSTM(400, 1150)
), WeightDrop(
(module): LSTM(1150, 1150)
), WeightDrop(
(module): LSTM(1150, 400)
)]
Using []
Args: Namespace(alpha=2, batch_size=80, beta=1, bptt=70, clip=0.25, cuda=False, data='data/wikitext-2', dropout=0.4, dropoute=0.1, dropouth=0.2, dropouti=0.65, emsize=400, epochs=750, log_interval=200, lr=30, model='LSTM', nhid=1150, nlayers=3, nonmono=5, optimizer='sgd', resume='', save='WT2.pt', seed=1882, tied=True, wdecay=1.2e-06, wdrop=0.5, when=[-1])
Model total parameters: 33556078
Traceback (most recent call last):
File "main.py", line 242, in
train()
File "main.py", line 198, in train
output, hidden, rnn_hs, dropped_rnn_hs = model(data, hidden, return_h=True)
File "/home/sam/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/sam/Documents/NLP/awd-lstm-lm/model.py", line 81, in forward
raw_output, new_h = rnn(raw_output, hidden[l])
File "/home/sam/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/sam/Documents/NLP/awd-lstm-lm/weight_drop.py", line 47, in forward
return self.module.forward(*args)
File "/home/sam/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/modules/rnn.py", line 179, in forward
self.dropout, self.training, self.bidirectional, self.batch_first)
RuntimeError: t() expects a 2D tensor, but self is 1D

This could be because of my version of pytorch.

Any suggestions?

[ink-pad]

Hello, please refer : #86 (comment) !