textgenrnn icon indicating copy to clipboard operation
textgenrnn copied to clipboard

Error while training new model

Open Karmanoid opened this issue 5 years ago • 1 comments

I'm using an example from notebook:

`texts = ['Never gonna give you up, never gonna let you down', 'Never gonna run around and desert you', 'Never gonna make you cry, never gonna say goodbye', 'Never gonna tell a lie and hurt you']

textgen.train_on_texts(texts, num_epochs=2, gen_epochs=2)`

but getting an error:

File "//anaconda3/lib/python3.6/site-packages/textgenrnn/textgenrnn.py", line 67, in init weights_path=weights_path)

File "//anaconda3/lib/python3.6/site-packages/textgenrnn/model.py", line 32, in textgenrnn_model attention = AttentionWeightedAverage(name='attention')(seq_concat)

File "//anaconda3/lib/python3.6/site-packages/textgenrnn/AttentionWeightedAverage.py", line 17, in init super(AttentionWeightedAverage, self).init(** kwargs)

TypeError: super(type, obj): obj must be an instance or subtype of type

Does anybody solve this problem?

Karmanoid avatar May 04 '19 10:05 Karmanoid

you need to make a txt file and use this code

import textgenrnn from textgenrnn import textgenrnn textgen = textgenrnn() textgen.train_from_file('txt file name here.txt', num_epochs=10) textgen.generate(15, temperature=1.0)

breadbrowser avatar Jul 06 '22 00:07 breadbrowser