The default model parameters worked well for me. However, when I changed the batch size for trainval_2nd.prototxt train phase from 4 to 2, I got the following losses which is strange. (With batch size 4 the loss is usually less than 1)
Train net output #38: loss_bbox = nan (* 1 = nan loss)
Train net output #39: loss_cls = 87.3365 (* 1 = 87.3365 loss)
Hi,
The default model parameters worked well for me. However, when I changed the batch size for trainval_2nd.prototxt train phase from 4 to 2, I got the following losses which is strange. (With batch size 4 the loss is usually less than 1)
Any idea what is the issue?