Hi, I’m trying to compare some policies, but I got some problems when using Keras as policy. In particular, when I run this command: rasa train core -c config-keras.yml config-emb.yml -s data/stories_training.md --out comparison_models/keras_emb I get this error: Traceback (most recent call last): File "_mt19937.pyx", line 178, in numpy.random._mt19937.MT19937._legacy_seeding TypeError: 'str' object cannot be interpreted as an integer During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/usr/local/bin/rasa", line 8, in <module> sys.exit(main()) File "/usr/local/lib/python3.6/dist-packages/rasa/__main__.py", line 76, in main cmdline_arguments.func(cmdline_arguments) File "/usr/local/lib/python3.6/dist-packages/rasa/cli/train.py", line 118, in train_core do_compare_training(args, story_file, additional_arguments) File "uvloop/loop.pyx", line 1456, in uvloop.loop.Loop.run_until_complete File "/usr/local/lib/python3.6/dist-packages/rasa/core/train.py", line 160, in do_compare_training get_no_of_stories(args.stories, args.domain), File "/usr/local/lib/python3.6/dist-packages/rasa/core/train.py", line 120, in train_comparison_models model.model_fingerprint(file_importer), File "/usr/local/lib/python3.6/dist-packages/rasa/core/train.py", line 67, in train agent.train(training_data, **additional_arguments) File "/usr/local/lib/python3.6/dist-packages/rasa/core/agent.py", line 722, in train self.policy_ensemble.train(training_trackers, self.domain, **kwargs) File "/usr/local/lib/python3.6/dist-packages/rasa/core/policies/ensemble.py", line 126, in train policy.train(training_trackers, domain, **kwargs) File "/usr/local/lib/python3.6/dist-packages/rasa/core/policies/keras_policy.py", line 167, in train np.random.seed(self.random_seed) File "mtrand.pyx", line 244, in numpy.random.mtrand.RandomState.seed File "_mt19937.pyx", line 166, in numpy.random._mt19937.MT19937._legacy_seeding File "_mt19937.pyx", line 186, in numpy.random._mt19937.MT19937._legacy_seeding TypeError: Cannot cast array from dtype('<U4') to dtype('int64') according to the rule 'safe' Does anybody know how to solve this? Thank you, Tiziano

How does your config-keras.yml file look like? Seems like you are trying to pass an invalid random seed according to the error.

Problem with Keras - Cannot cast array

tiziano (Tiziano Labruna) February 18, 2020, 9:21am 5

Yes, it was just a try for understanding how it worked, but that’s fine.

Could you please also help me to understand this?

Thank you

Topic		Replies	Views
TypeError: '>' not supported between instances of 'NoneType' and 'int' in probabilities_using_best_policy Rasa Open Source	0	2208	December 5, 2019
TypeError: can't pickle _thread.RLock objects Rasa Open Source	2	9620	October 17, 2019
Rasa train: TypeError: '>' not supported between instances of 'str' and 'int' Rasa Open Source	0	128	April 23, 2023
TyperError in Keras Policy Rasa Open Source	3	2538	November 21, 2018
RASA 1.0 HTTP API /model/train error Rasa Open Source	4	2037	June 14, 2019