Conversation
| assert not ent._sum_of_entropies.requires_grad | ||
|
|
||
|
|
||
| @pytest.mark.distributed |
There was a problem hiding this comment.
For distributed config tests, could you please rewrite them using new testing formalism that we are trying to adopt. Here is an example of the code to inspire of:
ignite/tests/ignite/metrics/test_recall.py
Lines 422 to 426 in 5fe7443
Here is a PR showing how to pass from old code to the new one:
https://github.com/pytorch/ignite/pull/3208/files#diff-c56c264ef288f88e5738e9ad22de66dffd4c58d2e656eb62e8dbaa678672317d
Thanks!
|
@kzkadc can you please run |
|
@kzkadc this failure is related: https://github.com/pytorch/ignite/actions/runs/8391979913/job/22983553399?pr=3210#step:9:345 |
Description: adds Entropy metric.$H=\sum_c - p_c \log p_c$ , where $p_c$ is the predicted probability for $c$ -th class.
Entropy is often used when evaluating uncertainty of classification predictions.
It is computed as
Check list: