I wanted to run rasa test to see how I was doing on my data. I just copied and pasted some of stories.yml to tests as test_stories.yml just to see how it did and I get the following error for some reason. It doesn’t look like a Rasa error.
2021-07-24 15:13:05 INFO rasa.model - Loading model models/20210724-143228.tar.gz...
2021-07-24 15:13:06.032369: E tensorflow/stream_executor/cuda/cuda_driver.cc:314] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected
/home/nicholaslee/anaconda3/envs/rasa/lib/python3.8/site-packages/rasa/utils/train_utils.py:601: UserWarning: model_confidence is set to `softmax`. It is recommended to try using `model_confidence=linear_norm` to make it easier to tune fallback thresholds.
rasa.shared.utils.io.raise_warning(
/home/nicholaslee/anaconda3/envs/rasa/lib/python3.8/site-packages/rasa/shared/utils/io.py:97: UserWarning: the value of 'evaluate_every_number_of_epochs' is greater than the value of 'epochs'. No evaluation will occur.
Processed story blocks: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 1973.09it/s, # trackers=1]
2021-07-24 15:13:27 INFO rasa.core.test - Evaluating 4 stories
Progress:
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 13.09it/s]
2021-07-24 15:13:28 INFO rasa.core.test - Finished collecting predictions.
2021-07-24 15:13:28 INFO rasa.core.test - Evaluation Results on END-TO-END level:
2021-07-24 15:13:28 INFO rasa.core.test - Correct: 4 / 4
2021-07-24 15:13:28 INFO rasa.core.test - Accuracy: 1.000
Traceback (most recent call last):
File "/home/nicholaslee/anaconda3/envs/rasa/bin/rasa", line 8, in <module>
sys.exit(main())
File "/home/nicholaslee/anaconda3/envs/rasa/lib/python3.8/site-packages/rasa/__main__.py", line 117, in main
cmdline_arguments.func(cmdline_arguments)
File "/home/nicholaslee/anaconda3/envs/rasa/lib/python3.8/site-packages/rasa/cli/test.py", line 237, in test
run_core_test(args)
File "/home/nicholaslee/anaconda3/envs/rasa/lib/python3.8/site-packages/rasa/cli/test.py", line 108, in run_core_test
test_core(
File "/home/nicholaslee/anaconda3/envs/rasa/lib/python3.8/site-packages/rasa/model_testing.py", line 182, in test_core
rasa.utils.common.run_in_loop(
File "/home/nicholaslee/anaconda3/envs/rasa/lib/python3.8/site-packages/rasa/utils/common.py", line 296, in run_in_loop
result = loop.run_until_complete(f)
File "uvloop/loop.pyx", line 1456, in uvloop.loop.Loop.run_until_complete
File "/home/nicholaslee/anaconda3/envs/rasa/lib/python3.8/site-packages/rasa/core/test.py", line 905, in test
targets, predictions = evaluation_store.serialise()
File "/home/nicholaslee/anaconda3/envs/rasa/lib/python3.8/site-packages/rasa/core/test.py", line 216, in serialise
entity_targets = sorted(
TypeError: '<' not supported between instances of 'NoneType' and 'NoneType'