luminoth icon indicating copy to clipboard operation
luminoth copied to clipboard

Published 20 hours ago • verified publisher icon tryolabs

nan train loss while training SSD

Open sbhavani opened this issue 5 years ago • 1 comments

Getting train_loss: nan at every step running training for SSD. I tried varying batch_size and learning_rate but still no improvement.

InvalidArgumentError (see above for traceback): Nan in summary histogram for: ssd/ssd_feature_extractor/conv_4_3_norm/conv4_3_normalized_hist

sbhavani avatar Apr 08 '19 03:04 sbhavani

same problem

afaq-ahmad avatar Oct 23 '19 06:10 afaq-ahmad