You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi,
I wanted to use the forward transfer metric and I selected it as forward_transfer_metrics(experience=True, stream=True). I have also set eval_every = 1 in the strategy template. Still I get the following error while evaluating with the whole test stream at once.
Any ideas or solutions? Thnx!
Traceback (most recent call last):
File "/home/aku7rng/git/generalized_timeseries_processing/internal_backbone/CL_SOTA_nonIID.py", line 304, in <module>
main(data)
File "/home/aku7rng/git/generalized_timeseries_processing/internal_backbone/CL_SOTA_nonIID.py", line 256, in main
test_results_stream = strategy.eval(test_stream)
File "/home/aku7rng/.conda/envs/sud_env/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/aku7rng/.conda/envs/sud_env/lib/python3.9/site-packages/avalanche/training/templates/base_sgd.py", line 226, in eval
super().eval(exp_list, **kwargs)
File "/home/aku7rng/.conda/envs/sud_env/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/aku7rng/.conda/envs/sud_env/lib/python3.9/site-packages/avalanche/training/templates/base.py", line 213, in eval
self._after_eval_exp(**kwargs)
File "/home/aku7rng/.conda/envs/sud_env/lib/python3.9/site-packages/avalanche/training/templates/base.py", line 341, in _after_eval_exp
trigger_plugins(self, "after_eval_exp", **kwargs)
File "/home/aku7rng/.conda/envs/sud_env/lib/python3.9/site-packages/avalanche/training/utils.py", line 75, in trigger_plugins
getattr(p, event)(strategy, **kwargs)
File "/home/aku7rng/.conda/envs/sud_env/lib/python3.9/site-packages/avalanche/training/plugins/evaluation.py", line 222, in fun
return self._update_metrics_and_loggers(strat, item)
File "/home/aku7rng/.conda/envs/sud_env/lib/python3.9/site-packages/avalanche/training/plugins/evaluation.py", line 160, in _update_metrics_and_loggers
metric_result = getattr(metric, callback)(strategy)
File "/home/aku7rng/.conda/envs/sud_env/lib/python3.9/site-packages/avalanche/evaluation/metrics/forward_transfer.py", line 238, in after_eval_exp
return self._package_result(strategy)
File "/home/aku7rng/.conda/envs/sud_env/lib/python3.9/site-packages/avalanche/evaluation/metrics/forward_transfer.py", line 246, in _package_result
result = self.result_key(k=self.eval_exp_id)
File "/home/aku7rng/.conda/envs/sud_env/lib/python3.9/site-packages/avalanche/evaluation/metrics/forward_transfer.py", line 296, in result_key
return self.forward_transfer.result_key(k=k)
File "/home/aku7rng/.conda/envs/sud_env/lib/python3.9/site-packages/avalanche/evaluation/metrics/forward_transfer.py", line 87, in result_key
return self.previous[k] - self.initial[k]
KeyError: 1
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi,
I wanted to use the forward transfer metric and I selected it as forward_transfer_metrics(experience=True, stream=True). I have also set eval_every = 1 in the strategy template. Still I get the following error while evaluating with the whole test stream at once.
Any ideas or solutions? Thnx!
Beta Was this translation helpful? Give feedback.
All reactions