Hello again, I found out strange thing. When training TinyYOLO with pretrained weights and if all data (all batches) has same dimensions, everything is fine. But if every batch has different data dimensions (same dimensions in actual batch, but different between other batches) training score goes i…

TinyYOLO training goes into NaN with cuDNN

treo Split this topic April 6, 2020, 3:01pm 19

Topic		Replies	Views
TinyYolo training goes into NaN with CPU Backend DL4J	6	987	April 16, 2020
Simple CNN predicts NaNs DL4J	3	504	November 2, 2020
Tiny YOLO PredictedObjects NaN DL4J	14	2142	June 18, 2024
NaNs present in prediction DL4J	3	1417	March 23, 2021
NaN on arm server DL4J	20	1474	December 28, 2020