On Wed, Mar 23, 2022, 09:43 Akim Tsvigun ***@***.***> wrote: Hi, I am inspecting the fields of application of BatchBald. I am using the get_batchbald_batch function from https://github.com/BlackHC/batchbald_redux/blob/master/01_batchbald.ipynb Here is an example: we have 3 samples with 2 mc inferences for each with 4 classes. The first two examples are totally identical, while the third is completely different yet has slightly lower BALD score (due to smaller fluctuation of probabilities across mc runs): log_probs_N_K_C = torch.Tensor([ [[0.1, 0.2, 0.3, 0.4], [0.15, 0.15, 0.3, 0.4]], [[0.1, 0.2, 0.3, 0.4], [0.15, 0.15, 0.3, 0.4]], [[0.4, 0.3, 0.2, 0.1], [0.4, 0.3, 0.16, 0.14]], ]).log() I hoped BatchBald would be useful in such a case since it queries diverse instances for the batch. Yet, it queries two duplicate examples: get_batchbald_batch(log_probs_N_K_C, batch_size=2, num_samples=3) outputs [0, 1]. I wonder whether this is the expected behavior of the algorithm or some bugs in the code may be present. Thank you for your attention! — Reply to this email directly, view it on GitHub <#16>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAFSBYHKROHLSHLXH3OMO53VBLRVZANCNFSM5RNOFFJA> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

On Wed, Mar 23, 2022, 12:10 Akim Tsvigun ***@***.***> wrote: This does not seem to affect: the following code returns with a success. log_probs_N_K_C = torch.Tensor([ [[0.1, 0.2, 0.3, 0.4], [0.15, 0.15, 0.3, 0.4]], [[0.1, 0.2, 0.3, 0.4], [0.15, 0.15, 0.3, 0.4]], [[0.4, 0.3, 0.2, 0.1], [0.4, 0.3, 0.16, 0.14]], ]).log() for n_samples in range(2, 100): assert get_batchbald_batch(log_probs_N_K_C, batch_size=2, num_samples=n_samples).indices == [0, 1] — Reply to this email directly, view it on GitHub <#16 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAFSBYCEFALI6IJAPBGHV2LVBMC37ANCNFSM5RNOFFJA> . You are receiving this because you commented.Message ID: ***@***.***>