Open ashley-mv opened 4 years ago
Hello, have you solved this problem? I also met the same problem
Hello, I also met the problem+1, :( . Have you solved this problem?
I found a solution! When the batch decreases, the lr should decrease. The following are my parameters: batch = 8; subdivisions = 4; lr = 0.0001;
It works fine!
Hello, The number of proposals are reduced to zeros after a few iterations, and later the loss becomes nan. VOC dataset is used for training. Has anyone run into the same problem?