03/08/2018 11:47:17 updates[ 12081] train loss[0.82557] remaining[0:01:19]
03/08/2018 11:47:54 updates[ 12161] train loss[0.82523] remaining[0:00:46]
03/08/2018 11:48:30 updates[ 12241] train loss[0.82464] remaining[0:00:12]
/F/FusionModel/layers.py:184: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
alpha_flat = F.softmax(scores.view(-1, x2.size(1)))
/F/FusionModel/layers.py:211: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
alpha = F.softmax(scores)
Traceback (most recent call last):
File "train.py", line 181, in
main()
File "train.py", line 147, in main
predictions.extend(model.predict(batch))
File "/F/FusionModel/model.py", line 109, in predict
scores = self.network(inputs) # output: [batch_size, 3]
File "/home/xxx/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 325, in call
result = self.forward(input, *kwargs)
File "/FusionModel/FusionNet.py", line 129, in forward
_, x1_cove = self.CoVe(x1, x1_mask)
File "/home/xxx/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 325, in call
result = self.forward(input, **kwargs)
File “/F/FusionModel/layers.py", line 128, in forward
emb = self.embedding if self.training else self.eval_embed
File "/home/xxx/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 366, in getattr
type(self).name, name))
AttributeError: 'MTLSTM' object has no attribute 'eval_embed'
03/08/2018 11:47:17 updates[ 12081] train loss[0.82557] remaining[0:01:19] 03/08/2018 11:47:54 updates[ 12161] train loss[0.82523] remaining[0:00:46] 03/08/2018 11:48:30 updates[ 12241] train loss[0.82464] remaining[0:00:12] /F/FusionModel/layers.py:184: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument. alpha_flat = F.softmax(scores.view(-1, x2.size(1))) /F/FusionModel/layers.py:211: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument. alpha = F.softmax(scores) Traceback (most recent call last): File "train.py", line 181, in
main()
File "train.py", line 147, in main
predictions.extend(model.predict(batch))
File "/F/FusionModel/model.py", line 109, in predict
scores = self.network(inputs) # output: [batch_size, 3]
File "/home/xxx/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 325, in call
result = self.forward(input, *kwargs)
File "/FusionModel/FusionNet.py", line 129, in forward
_, x1_cove = self.CoVe(x1, x1_mask)
File "/home/xxx/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 325, in call
result = self.forward(input, **kwargs)
File “/F/FusionModel/layers.py", line 128, in forward
emb = self.embedding if self.training else self.eval_embed
File "/home/xxx/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 366, in getattr
type(self).name, name))
AttributeError: 'MTLSTM' object has no attribute 'eval_embed'