-
Notifications
You must be signed in to change notification settings - Fork 843
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.
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
NotImplementedError in train2.py #106
Comments
Please help me resolve the issue. I beg of you. :) |
hi YashBangera7 how did you run train 1 did it like the python train1.py '22' |
@ozler i ran it like this : python train1.py -case "TIMIT_RUN2_carl" -gpu 0 |
stuck at the same point :( |
I am also trying to understand this error. (In train1.py) |
It looks like the function that is being called in the tensorboard model_desc folder has been depreciated, the body of the function has been totally removed and just throws the error: (see line 136 in model_desc.py) Link to model_desc.py history |
For a hack fix, this version/release of tensorpack seems to be compiling: (0.9.0.1) https://github.com/tensorpack/tensorpack/archive/0.9.0.1.zip |
(dlwin36) D:\Deep Voice\deep-voice-conversion-master>python train2.py -ckpt model-936500
case: None, logdir1: cases/None/train1, logdir2: cases/None/train2
[0417 02:48:31 @logger.py:125] WRN Log directory cases/None/train2 exists! Use 'd' to delete it.
[0417 02:48:31 @logger.py:128] WRN If you're resuming from a previous run, you can choose to keep it.
Press any other key to exit.
Select Action: k (keep) / d (delete) / q (quit):k
[0417 02:48:38 @logger.py:83] Existing log file 'cases/None/train2\log.log' backuped to 'cases/None/train2\log.log.0417-024838'
[0417 02:48:38 @logger.py:90] Argv: train2.py -ckpt model-936500
[0417 02:48:38 @parallel.py:183] WRN MultiProcessPrefetchData does support Windows. However, Windows requires more strict picklability on processes, which may lead of failure on some of the code.
[0417 02:48:38 @parallel.py:193] [MultiProcessPrefetchData] Will fork a dataflow more than one times. This assumes the datapoints are i.i.d.
[0417 02:49:11 @sesscreate.py:38] WRN User-provided custom session config may not work due to TF bugs. See tensorpack/tensorpack#497 for workarounds.
Traceback (most recent call last):
File "train2.py", line 93, in
train(args, logdir1=logdir_train1, logdir2=logdir_train2)
File "train2.py", line 62, in train
launch_train_with_config(train_conf, trainer=trainer)
File "C:\Users\Yash\anaconda\envs\dlwin36\lib\site-packages\tensorpack\train\interface.py", line 90, in launch_train_with_config
model.get_input_signature(), input,
File "C:\Users\Yash\anaconda\envs\dlwin36\lib\site-packages\tensorpack\utils\argtools.py", line 200, in wrapper
value = func(*args, **kwargs)
File "C:\Users\Yash\anaconda\envs\dlwin36\lib\site-packages\tensorpack\graph_builder\model_desc.py", line 86, in get_input_signature
inputs = self.inputs()
File "C:\Users\Yash\anaconda\envs\dlwin36\lib\site-packages\tensorpack\graph_builder\model_desc.py", line 116, in inputs
raise NotImplementedError()
NotImplementedError
The text was updated successfully, but these errors were encountered: