Reply to Error about tensorflow_novelist on Mon, 08 Apr 2019 05:12:54 GMT

William — Mon, 08 Apr 2019 05:12:54 GMT

Got error when running python3 main.py --type f --no-train, waiting for help.
I played tensorflow_poem, it is impressed me a lot, now, I am curious about tensorflow_novelist. How can I fix it?

File "~/Programming/myGithub/tensorflow_novelist/inference/fiction.py", line 154, in main
running(is_train)
File "/Users/william/Programming/myGithub/tensorflow_novelist/inference/fiction.py", line 46, in running
if not os.path.exists(FLAGS.checkpoints_dir):
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/platform/flags.py", line 84, in getattr
wrapped(_sys.argv)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/absl/flags/_flagvalues.py", line 633, in call
name, value, suggestions=suggestions)
absl.flags._exceptions.UnrecognizedFlagError: Unknown command line flag 'type'

Reply to Error about tensorflow_novelist on Tue, 09 Apr 2019 01:39:00 GMT

刘看山 — Tue, 09 Apr 2019 01:39:00 GMT

谢邀。

已经不玩NLP许久了，说到文本生成，我目前还只停留在RNN层次，但现在各种transform结构，BERT等不绝于耳，似乎NLP领域已经迎来了全新的产业革新。
关于文本生成，由其是长文本生成，可以尝试一下最新的transform， BERT等体系架构或者与训练模型，结合GAN来尝试。
欢迎继续来社区交流看法与新的发现！