jackhaha363 / bbbrnn Goto Github PK

Traceback (most recent call last):
File "/Users/zyl/Downloads/BBBRNN-master/main.py", line 249, in
train_loss, train_nll, train_kl = train()
File "/Users/zyl/Downloads/BBBRNN-master/main.py", line 187, in train
hidden = repackage_hidden(hidden)
File "/Users/zyl/Downloads/BBBRNN-master/main.py", line 131, in repackage_hidden
return tuple(repackage_hidden(v) for v in h)
File "/Users/zyl/Downloads/BBBRNN-master/main.py", line 131, in
return tuple(repackage_hidden(v) for v in h)
File "/Users/zyl/Downloads/BBBRNN-master/main.py", line 131, in repackage_hidden
return tuple(repackage_hidden(v) for v in h)
File "/Users/zyl/Downloads/BBBRNN-master/main.py", line 131, in
return tuple(repackage_hidden(v) for v in h)
File "/Users/zyl/Downloads/BBBRNN-master/main.py", line 131, in repackage_hidden
return tuple(repackage_hidden(v) for v in h)
File "/Users/zyl/Downloads/BBBRNN-master/main.py", line 131, in
return tuple(repackage_hidden(v) for v in h)
File "/Users/zyl/Downloads/BBBRNN-master/main.py", line 131, in repackage_hidden
return tuple(repackage_hidden(v) for v in h)
File "/Users/zyl/Downloads/BBBRNN-master/main.py", line 131, in
return tuple(repackage_hidden(v) for v in h)
File "/Users/zyl/Downloads/BBBRNN-master/main.py", line 131, in repackage_hidden
return tuple(repackage_hidden(v) for v in h)
File "/Users/zyl/opt/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/_tensor.py", line 915, in iter
raise TypeError("iteration over a 0-d tensor")
TypeError: iteration over a 0-d tensor

Good job! Thanks for sharing it!
I have some issues when I use BayesianRNN of your project into my own work. I found that the KL loss is so large which is up to 9.00*10^8 and my prediction loss is 20.00 which is normal, for each time step. So the training process can not continue because the KL loss is not regular. So I dont know the reson why this issue occurs.
I would appreciate it if you can give me some kinds of tips for fixing it or any suggestio