Loss function value is nan about a-pytorch-tutorial-to-object-detection HOT 5 CLOSED

try reducing batch size and gradient clipping as sgrvinod noted

im using batch size 8 and gradient clipping value 1

from a-pytorch-tutorial-to-object-detection.

@toomy0toons Thanks for the response. I found that log of negative decimal in the cxcy_to_gcxgcy function gives nan values.. I have to make them absolute to give proper values. How come you did not get any nan values?. If the input to the log function is negative decimal it gives nan.

from a-pytorch-tutorial-to-object-detection.

@Eloneinstein
center cords should be positive as it measures distance in ratio so the function should always return positive.
are you using a custom dataset?
if so match the input to xmin,ymin,xmax,ymax. Same error happened to me when i was feeding different dataset which is was xmax,ymin, xmin, ymax

from a-pytorch-tutorial-to-object-detection.

@toomy0toons . I am using the same VOC 2007 dataset. I will check for the order of the coordinates. What is the loss value you were getting?

from a-pytorch-tutorial-to-object-detection.

@toomy0toons . Thanks a lot for the solution. I put the coordinates in the wrong order. Thanks again.

from a-pytorch-tutorial-to-object-detection.