You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Nov 16, 2023. It is now read-only.
When I run this line of code, it gives the following error:
> train_lm("shakespeare.txt", epochs, max_num_minibatches)
Error in py_call_impl(callable, dots$args, dots$keywords) :
AttributeError: 'Variable' object has no attribute 'astype'
Detailed traceback:
File "D:\anaconda3\envs\cntk-py36\lib\site-packages\cntk\ops\functions.py", line 393, in __call__
_, output_map = self.forward(arg_map, outputs)
File "D:\anaconda3\envs\cntk-py36\lib\site-packages\cntk\internal\swig_helper.py", line 69, in wrapper
result = f(*args, **kwds)
File "D:\anaconda3\envs\cntk-py36\lib\site-packages\cntk\ops\functions.py", line 755, in forward
None, device)
File "D:\anaconda3\envs\cntk-py36\lib\site-packages\cntk\internal\sanitize.py", line 431, in sanitize_var_map
batch = sanitize_batch(var, batch, seq_starts, device)
File "D:\anaconda3\envs\cntk-py36\lib\site-packages\cntk\internal\swig_helper.py", line 69, in wrapper
result = f(*args, **kwds)
File "D:\anaconda3\envs\cntk-py36\lib\site-packages\cntk\internal\sanitize.py", line 200, in sanitize_batch
return Value.create(var, batch, seq_starts, device)
File "D:\anaconda3\envs\cntk-py
Called from: py_call_impl(callable, dots$args, dots$keywords)
A deeper analysis identified that the problem actually happens at this section of the train_lm() function:
z <- model(input_sequence)
Help on this issue will be greatly appreciated!
The text was updated successfully, but these errors were encountered:
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
I ran into a problem while attempting to follow the code exactly from the provided CharacterLM.rmd in the vignettes folder .
When I run this line of code, it gives the following error:
A deeper analysis identified that the problem actually happens at this section of the train_lm() function:
z <- model(input_sequence)
Help on this issue will be greatly appreciated!
The text was updated successfully, but these errors were encountered: