@treo Hi, I am following this thread with interest and I am testing a lot with different datasets and I have observed strange learning curves and NaN values as well. It is only a feeling but I think it is not related to cuDNN in general but more deeply in the computational layers of Yolo, it rather …

TinyYolo training goes into NaN with CPU Backend

treo April 6, 2020, 9:49am 4

Just to make sure that I did get that right: Are you getting NaN problems with the CPU backend with larger batches, too? Or is it only cuDNN?

Topic		Replies	Views
TinyYOLO training goes into NaN with cuDNN DL4J	19	1696	April 15, 2020
Random seed with GPU backend DL4J	12	1003	February 24, 2020
Manually destroying AMDSI workspace Debug by ND4J AsyncMultiDataSetIterator ND4J	1	441	February 6, 2021
Simple CNN predicts NaNs DL4J	3	500	November 2, 2020
Help with TinyYoloHouseNumberDetection example	2	37	June 14, 2024