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	904	April 16, 2020
Simple CNN predicts NaNs DL4J	3	468	November 2, 2020
Random seed with GPU backend DL4J	12	910	February 24, 2020
More Batch normalization problems with 1dconvolution DL4J	1	326	April 9, 2021
BatchNormalization Layer only support single int as nIn and nOut? DL4J	6	408	October 6, 2020