3d-mri-brain-tumor-segmentation-using-autoencoder-regularization icon indicating copy to clipboard operation
3d-mri-brain-tumor-segmentation-using-autoencoder-regularization copied to clipboard

Published 20 hours ago • verified publisher icon IAmSuyogJadhav

Decoder loss and dice coefficient is 0 even after i trained it for 90 epochs?

Open sneh-debug opened this issue 5 years ago • 2 comments

Epoch 90/90 1/2 [==============>...............] - ETA: 15s - loss: 0.0271 - Dec_GT_Output_loss: 0.0000e+00 - Dec_VAE_Output_loss: 0.0271 - Dec_GT_Output_d2/2 [==============================] - 30s 15s/step - loss: 0.0282 - Dec_GT_Output_loss: 0.0000e+00 - Dec_VAE_Output_loss: 0.0282 - Dec_GT_Output_dice_coefficient: 0.0000e+00 - Dec_VAE_Output_dice_coefficient: 0.8795 I trained for epoch 90, but the decoder loss and dice coefficient remained 0

sneh-debug avatar Feb 14 '20 09:02 sneh-debug

I have the same problem

FBehrad avatar Jun 15 '20 08:06 FBehrad

Hi, I think you used small dataset, As you showed, you only training 2 part per epoch

vvuonghn avatar Jun 29 '20 06:06 vvuonghn